1. |
- Ahlskog-Björkman, Eva, et al.
(författare)
-
Barn och fred. En pilotstudie om förskolebarns förståelse av fred
- 2018
-
Ingår i: Nordidactica. - Karlstad : CSD Karlstad. - 2000-9879. ; :2018:4, s. 65-87
-
Tidskriftsartikel (refereegranskat)abstract
- Enligt FN:s mål om hållbar utveckling (Agenda 2030) betonas bland annat främjandet av en kultur av fred och icke-våld. Utvecklingen i finländska styrdokument för förskolan visar däremot att temat fred har nedtonats. Denna studie vill genom ämnesdidaktisk samverkan mellan bildkonst och religion synliggöra 6-åringars förståelse av fred, deras sätt att samtala om och i teckningar gestalta ett liv i fred med varandra. Den kvalitativa temaanalysen visade att barn i denna pilotstudie förstår fred som tillstånd, fred som relationer, fred som förhandlingar och fred som möte och handling. Samtal kring barnens teckningar och de visuella konkretiseringarna stöder tolkningen. Pilotstudien har genom pedagogiska och ämnesdidaktiska perspektiv på lärande för fred uppmärksammat vikten av att barns lärandeprocesser om fred, icke-våld och globalt medborgaskap behöver beakta kravet på tid, rum, språk och struktur för interaktion, tolkning, fördjupning och handling.
|
|
2. |
- Baldvinsson, Jon R., et al.
(författare)
-
IL-GAN : Rare Sample Generation via Incremental Learning in GANs
- 2022
-
Ingår i: 2022 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM 2022). - : Institute of Electrical and Electronics Engineers (IEEE). ; , s. 621-626
-
Konferensbidrag (refereegranskat)abstract
- Industry 4.0 imposes strict requirements on the fifth generation of wireless systems (5G), such as high reliability, high availability, and low latency. Guaranteeing such requirements implies that system failures should occur with an extremely low probability. However, some applications (e.g., training a reinforcement learning algorithm to operate in highly reliable systems or rare event simulations) require access to a broad range of observed failures and extreme values, preferably in a short time. In this paper, we propose IL-GAN, an alternative training framework for generative adversarial networks (GANs), which leverages incremental learning (IL) to enable the generation to learn the tail behavior of the distribution using only a few samples. We validate the proposed IL-GAN with data from 5G simulations on a factory automation scenario and real measurements gathered from various video streaming platforms. Our evaluations show that, compared to the state-of-the-art, our solution can significantly improve the learning and generation performance, not only for the tail distribution but also for the rest of the distribution.
|
|
3. |
- Bekiroglu, Y., et al.
(författare)
-
Visual and tactile 3D point cloud data from real robots for shape modeling and completion
- 2020
-
Ingår i: Data in Brief. - : Elsevier. - 2352-3409. ; 30
-
Tidskriftsartikel (refereegranskat)abstract
- Representing 3D geometry for different tasks, e.g. rendering and reconstruction, is an important goal in different fields, such as computer graphics, computer vision and robotics. Robotic applications often require perception of object shape information extracted from sensory data that can be noisy and incomplete. This is a challenging task and in order to facilitate analysis of new methods and comparison of different approaches for shape modeling (e.g. surface estimation), completion and exploration, we provide real sensory data acquired from exploring various objects of different complexities. The dataset includes visual and tactile readings in the form of 3D point clouds obtained using two different robot setups that are equipped with visual and tactile sensors. During data collection, the robots touch the experiment objects in a predefined manner at various exploration configurations and gather visual and tactile points in the same coordinate frame based on calibration between the robots and the used cameras. The goal of this exhaustive exploration procedure is to sense unseen parts of the objects which are not visible to the cameras, but can be sensed via tactile sensors activated at touched areas. The data was used for shape completion and modeling via Implicit Surface representation and Gaussian-Process-based regression, in the work “Object shape estimation and modeling, based on sparse Gaussian process implicit surfaces, combining visual data and tactile exploration” [3], and also used partially in “Enhancing visual perception of shape through tactile glances” [4], both studying efficient exploration of objects to reduce number of touches.
|
|
4. |
|
|
5. |
- Bergström, Niklas, 1978-, et al.
(författare)
-
Active Scene Analysis
- 2010
-
Konferensbidrag (refereegranskat)
|
|
6. |
- Bergström, Niklas, 1978-, et al.
(författare)
-
Generating Object Hypotheses in Natural Scenes through Human-Robot Interaction
- 2011
-
Ingår i: 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS. - San Francisco : IEEE. - 9781612844541 ; , s. 827-833
-
Konferensbidrag (refereegranskat)abstract
- We propose a method for interactive modeling ofobjects and object relations based on real-time segmentation ofvideo sequences. In interaction with a human, the robot canperform multi-object segmentation through principled model-ing of physical constraints. The key contribution is an efficientmulti-labeling framework, that allows object modeling anddisambiguation in natural scenes. Object modeling and labelingis done in a real-time, to which hypotheses and constraintsdenoting relations between objects can be added incrementally.Through instructions such as key presses or spoken words, ascene can be segmented in regions corresponding to multiplephysical objects. The approach solves some of the difficultproblems related to disambiguation of objects merged due totheir direct physical contact. Results show that even a limited setof simple interactions with a human operator can substantiallyimprove segmentation results.
|
|
7. |
- Bergström, Niklas, 1978-, et al.
(författare)
-
Scene Understanding through Autonomous Interactive Perception
- 2011
-
Ingår i: Computer Vision Systems. - Berlin, Heidelberg : Springer Verlag. - 9783642239670 - 3642239676 ; , s. 153-162
-
Konferensbidrag (refereegranskat)abstract
- We propose a framework for detecting, extracting and mod-eling objects in natural scenes from multi-modal data. Our frameworkis iterative, exploiting different hypotheses in a complementary manner.We employ the framework in realistic scenarios, based on visual appear-ance and depth information. Using a robotic manipulator that interactswith the scene, object hypotheses generated using appearance informa-tion are confirmed through pushing. The framework is iterative, eachgenerated hypothesis is feeding into the subsequent one, continuously re-fining the predictions about the scene. We show results that demonstratethe synergic effect of applying multiple hypotheses for real-world sceneunderstanding. The method is efficient and performs in real-time.
|
|
8. |
- Bienkiewicz, Marta M. N., et al.
(författare)
-
Bridging the gap between emotion and joint action
- 2021
-
Ingår i: Neuroscience and Biobehavioral Reviews. - : Elsevier BV. - 0149-7634 .- 1873-7528. ; 131, s. 806-833
-
Tidskriftsartikel (refereegranskat)abstract
- Our daily human life is filled with a myriad of joint action moments, be it children playing, adults working together (i.e., team sports), or strangers navigating through a crowd. Joint action brings individuals (and embodiment of their emotions) together, in space and in time. Yet little is known about how individual emotions propagate through embodied presence in a group, and how joint action changes individual emotion. In fact, the multi-agent component is largely missing from neuroscience-based approaches to emotion, and reversely joint action research has not found a way yet to include emotion as one of the key parameters to model socio-motor interaction. In this review, we first identify the gap and then stockpile evidence showing strong entanglement between emotion and acting together from various branches of sciences. We propose an integrative approach to bridge the gap, highlight five research avenues to do so in behavioral neuroscience and digital sciences, and address some of the key challenges in the area faced by modern societies.
|
|
9. |
- Björkgren, Mårten, et al.
(författare)
-
En komparativ förståelse av ämnesdidaktiska prepositioner
- 2019
-
Ingår i: Nordidactica. - Karlstad : CSD Karlstad. - 2000-9879. ; :2019:3, s. 45-72
-
Tidskriftsartikel (refereegranskat)abstract
- The national curricular guidelines for basic education and upper secondary school require teachers to have a readiness to teach and cooperate in accordance with a holistic multidisciplinary principle. The teacher education programmes in Finland are challenged to develop research-based knowledge about learning processes in holistic multidisciplinary teaching concerning both theory and practice. In this article, focus is put on comparisons between the subject-didactic perspectives of Art, Religion, History, and Social Studies. Referring to Lindström, the prepositions about, in, with and through are used as a point of departure for the aesthetic fields. The comparison is based on the prepositional perspective and particularly focusses on the understanding of the didactic emphases and ambitions. The subject-comparative reflection between similarities and differences is based on a socio-cultural view of learning, and the perspectives qualification, socialisation and subjectification by Giert Biesta. The article contributes to a consciousness about meaningful subject-didactic prerequisites for holistic multidisciplinary cooperation.
|
|
10. |
|
|
11. |
- Björkman, Mårten, 1970-, et al.
(författare)
-
Active 3D scene segmentation and detection of unknown objects
- 2010
-
Ingår i: IEEE International Conference on Robotics and Automation (ICRA), Anchorage, USA. - : IEEE Robotics and Automation Society. - 9781424450381 ; , s. 3114-3120
-
Konferensbidrag (refereegranskat)abstract
- We present an active vision system for segmentationof visual scenes based on integration of several cues. The system serves as a visual front end for generation of object hypotheses for new, previously unseen objects in natural scenes. The system combines a set of foveal and peripheral cameraswhere, through a stereo based fixation process, object hypotheses are generated. In addition to considering the segmentation process in 3D, the main contribution of the paper is integration of different cues in a temporal framework and improvement of initial hypotheses over time.
|
|
12. |
- Björkman, Mårten, 1970-, et al.
(författare)
-
Active 3D Segmentation through Fixation of Previously Unseen Objects
- 2010
-
Ingår i: British Machine Vision Conference (BMVC), Aberystwyth, UK. - : BMVA Press. - 1901725405 ; , s. 119.1-119.11
-
Konferensbidrag (refereegranskat)abstract
- We present an approach for active segmentation based on integration of several cues.It serves as a framework for generation of object hypotheses of previously unseen objectsin natural scenes. Using an approximate Expectation-Maximisation method, the appearance,3D shape and size of objects are modelled in an iterative manner, with fixation usedfor unsupervised initialisation. To better cope with situations where an object is hard tosegregate from the surface it is placed on, a flat surface model is added to the typical twohypotheses used in classical figure-ground segmentation. The framework is further extendedto include modelling over time, in order to exploit temporal consistency for bettersegmentation and to facilitate tracking.
|
|
13. |
- Björkman, Mårten, 1970-, et al.
(författare)
-
Attending, Foveating and Recognizing Objects in Real World Scenes
- 2004
-
Ingår i: British Machine Vision Conference (BMVC), London, UK. - : BMVA Press. - 1901725251 ; , s. 227-236
-
Konferensbidrag (refereegranskat)abstract
- Recognition in cluttered real world scenes is a challenging problem. To find a particular object of interest within a reasonable time, a wide field of view is preferable. However, as we will show with practical experiments, robust recognition is easier if the object is foveated and subtends a considerable partof the visual field. In this paper a binocular system able to overcome these two conflicting requirements will be presented. The system consists of two sets of cameras, a wide field pair and a foveal one. From disparities a number of object hypotheses are generated. An attentional process based on hue and 3D size guides the foveal cameras towards the most salient regions. With the object foveated and segmented in 3D, recognition is performed using scale invariant features. The system is fully automised and runs at real-time speed.
|
|
14. |
- Björkman, Mårten, et al.
(författare)
-
Combination of foveal and peripheral vision for object recognition and pose estimation
- 2004
-
Ingår i: 2004 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1- 5, PROCEEDINGS. - 0780382323 ; , s. 5135-5140
-
Konferensbidrag (refereegranskat)abstract
- In this paper, we present a real-time vision system that integrates a number of algorithms using monocular and binocular cues to achieve robustness in realistic settings, for tasks such as object recognition, tracking and pose estimation. The system consists of two sets of binocular cameras; a peripheral set for disparity based attention and a foveal one for higher level processes. Thus the conflicting requirements of a wide field of view and high resolution can be overcome. One important property of the system is that the step from task specification through object recognition to pose estimation is completely automatic, combining both appearance and geometric models. Experimental evaluation is performed in a realistic indoor environment with occlusions, clutter, changing lighting and background conditions.
|
|
15. |
- Björkman, Mårten, 1970-, et al.
(författare)
-
Detecting, segmenting and tracking unknown objects using multi-label MRF inference
- 2014
-
Ingår i: Computer Vision and Image Understanding. - : Elsevier. - 1077-3142 .- 1090-235X. ; 118, s. 111-127
-
Tidskriftsartikel (refereegranskat)abstract
- This article presents a unified framework for detecting, segmenting and tracking unknown objects in everyday scenes, allowing for inspection of object hypotheses during interaction over time. A heterogeneous scene representation is proposed, with background regions modeled as a combinations of planar surfaces and uniform clutter, and foreground objects as 3D ellipsoids. Recent energy minimization methods based on loopy belief propagation, tree-reweighted message passing and graph cuts are studied for the purpose of multi-object segmentation and benchmarked in terms of segmentation quality, as well as computational speed and how easily methods can be adapted for parallel processing. One conclusion is that the choice of energy minimization method is less important than the way scenes are modeled. Proximities are more valuable for segmentation than similarity in colors, while the benefit of 3D information is limited. It is also shown through practical experiments that, with implementations on GPUs, multi-object segmentation and tracking using state-of-art MRF inference methods is feasible, despite the computational costs typically associated with such methods.
|
|
16. |
- Björkman, Mårten, 1970-, et al.
(författare)
-
Enhancing Visual Perception of Shape through Tactile Glances
- 2013
-
Ingår i: Intelligent Robots and Systems (IROS), 2013 IEEE/RSJ International Conference on. - : IEEE conference proceedings. - 2153-0866 .- 2153-0858. - 9781467363587 ; , s. 3180-3186
-
Konferensbidrag (refereegranskat)abstract
- Object shape information is an important parameter in robot grasping tasks. However, it may be difficult to obtain accurate models of novel objects due to incomplete and noisy sensory measurements. In addition, object shape may change due to frequent interaction with the object (cereal boxes, etc). In this paper, we present a probabilistic approach for learning object models based on visual and tactile perception through physical interaction with an object. Our robot explores unknown objects by touching them strategically at parts that are uncertain in terms of shape. The robot starts by using only visual features to form an initial hypothesis about the object shape, then gradually adds tactile measurements to refine the object model. Our experiments involve ten objects of varying shapes and sizes in a real setup. The results show that our method is capable of choosing a small number of touches to construct object models similar to real object shapes and to determine similarities among acquired models.
|
|
17. |
- Björkman, Mårten, 1970-, et al.
(författare)
-
Foveated Figure-Ground Segmentation and Its Role in Recognition
- 2005
-
Ingår i: BMVC 2005 - Proceedings of the British Machine Vision Conference 2005. - : British Machine Vision Association, BMVA. - 1901725294 - 1901725308 ; , s. 819-828
-
Konferensbidrag (refereegranskat)abstract
- Figure-ground segmentation and recognition are two interrelated processes. In this paper we present a method for foveated segmentation and evaluate it in the context of a binocular real-time recognition system. Segmentation is solved as a binary labeling problem using priors derived from the results ofa simplistic disparity method. Doing so we are able to cope with situations when the disparity range is very wide, situations that has rarely been considered, but appear frequently for narrow-field camera sets. Segmentation and recognition are then integrated into a system able to locate, attend to and recognise objects in typical cluttered indoor scenes. Finally, we try to answer two questions: is recognition really helped by segmentation and what is the benefit of multiple cues for recognition?
|
|
18. |
- Björkman, Mårten, et al.
(författare)
-
Learning to Disambiguate Object Hypotheses through Self-Exploration
- 2014
-
Ingår i: 14th IEEE-RAS International Conference onHumanoid Robots. - : IEEE Computer Society. - 2164-0572 .- 2164-0580. - 9781479971749 - 9781479971756
-
Konferensbidrag (refereegranskat)abstract
- We present a probabilistic learning framework to form object hypotheses through interaction with the environment. A robot learns how to manipulate objects through pushing actions to identify how many objects are present in the scene. We use a segmentation system that initializes object hypotheses based on RGBD data and adopt a reinforcement approach to learn the relations between pushing actions and their effects on object segmentations. Trained models are used to generate actions that result in minimum number of pushes on object groups, until either object separation events are observed or it is ensured that there is only one object acted on. We provide baseline experiments that show that a policy based on reinforcement learning for action selection results in fewer pushes, than if pushing actions were selected randomly.
|
|
19. |
|
|
20. |
- Björkman, Mårten, et al.
(författare)
-
Real-time epipolar geometry estimation of binocular stereo heads
- 2002
-
Ingår i: IEEE Transactions on Pattern Analysis and Machine Intelligence. - : Institute of Electrical and Electronics Engineers (IEEE). - 0162-8828 .- 1939-3539. ; 24:3, s. 425-432
-
Tidskriftsartikel (refereegranskat)abstract
- Stereo is an important cue for visually guided robots. While moving around in the world, such a robot can use dynamic fixation to overcome limitations in image resolution and field of view. In this paper, a binocular stereo system capable of dynamic fixation is presented. The external calibration is performed continuously taking temporal consistency into consideration, greatly simplifying the process. The essential matrix, which is estimated in real-time, is used to describe the epipolar geometry. It will be shown, how outliers can be identified and excluded from the calculations. An iterative approach based on a differential model of the optical flow, commonly used in structure from motion, is also presented and tested towards the essential matrix. The iterative method will be shown to be superior in terms of both computational speed and robustness, when the vergence angles are less than about 15degrees. For larger angles, the differential model is insufficient and the essential matrix is preferably used instead.
|
|
21. |
|
|
22. |
|
|
23. |
- Björkman, Mårten, et al.
(författare)
-
Vision in the real world : Finding, attending and recognizing objects
- 2006
-
Ingår i: International journal of imaging systems and technology (Print). - : Wiley. - 0899-9457 .- 1098-1098. ; 16:5, s. 189-208
-
Tidskriftsartikel (refereegranskat)abstract
- In this paper we discuss the notion of a seeing system that uses vision to interact with its environment. The requirements on such a system depend on the tasks it is involved in and should be evaluated with these in mind. Here we consider the task of finding and recognizing objects in the real world. After a discussion of the needed functionalities and issues about the design we present an integrated real-time vision system capable of finding, attending and recognizing objects in real settings. The system is based on a dual set of cameras, a wide field set for attention and a foveal one for recognition. The continuously running attentional process uses top-down object characteristics in terms of hue and 3D size. Recognition is performed with objects of interest foveated and segmented from its background. We describe the system structure as well as the different components in detail and present experimental evaluations of its overall performance.
|
|
24. |
|
|
25. |
|
|
26. |
- Bohg, Jeannette, et al.
(författare)
-
Strategies for Multi-Modal Scene Exploration
- 2010
-
Ingår i: IEEE/RSJ 2010 INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2010). - 9781424466757 ; , s. 4509-4515
-
Konferensbidrag (refereegranskat)abstract
- We propose a method for multi-modal scene exploration where initial object hypothesis formed by active visual segmentation are confirmed and augmented through haptic exploration with a robotic arm. We update the current belief about the state of the map with the detection results and predict yet unknown parts of the map with a Gaussian Process. We show that through the integration of different sensor modalities, we achieve a more complete scene model. We also show that the prediction of the scene structure leads to a valid scene representation even if the map is not fully traversed. Furthermore, we propose different exploration strategies and evaluate them both in simulation and on our robotic platform.
|
|
27. |
- Bütepage, Judith, et al.
(författare)
-
Imitating by Generating : Deep Generative Models for Imitation of Interactive Tasks
- 2020
-
Ingår i: Frontiers in Robotics and AI. - : Frontiers Media SA. - 2296-9144. ; 7
-
Tidskriftsartikel (refereegranskat)abstract
- To coordinate actions with an interaction partner requires a constant exchange of sensorimotor signals. Humans acquire these skills in infancy and early childhood mostly by imitation learning and active engagement with a skilled partner. They require the ability to predict and adapt to one's partner during an interaction. In this work we want to explore these ideas in a human-robot interaction setting in which a robot is required to learn interactive tasks from a combination of observational and kinesthetic learning. To this end, we propose a deep learning framework consisting of a number of components for (1) human and robot motion embedding, (2) motion prediction of the human partner, and (3) generation of robot joint trajectories matching the human motion. As long-term motion prediction methods often suffer from the problem of regression to the mean, our technical contribution here is a novel probabilistic latent variable model which does not predict in joint space but in latent space. To test the proposed method, we collect human-human interaction data and human-robot interaction data of four interactive tasks “hand-shake,” “hand-wave,” “parachute fist-bump,” and “rocket fist-bump.” We demonstrate experimentally the importance of predictive and adaptive components as well as low-level abstractions to successfully learn to imitate human behavior in interactive social tasks.
|
|
28. |
- Chen, Shuangshuang, 1992-, et al.
(författare)
-
Amortized Variational Inference for Road Friction Estimation
- 2020
-
Ingår i: 2020 IEEE Intelligent Vehicles Symposium (IV). - : Institute of Electrical and Electronics Engineers (IEEE). ; , s. 1777-1784, s. 1777-1784
-
Konferensbidrag (refereegranskat)abstract
- Road friction estimation concerns inference of the coefficient between the tire and road surface to facilitate active safety features. Current state-of-the-art methods lack generalization capability to cope with different tire characteristics and models are restricted when using Bayesian inference in estimation while recent supervised learning methods lack uncertainty prediction on estimates. This paper introduces variational inference to approximate intractable posterior of friction estimates and learns an amortized variational inference model from tire measurement data to facilitate probabilistic estimation while sustaining the flexibility of tire models. As a by-product, a probabilistic tire model can be learned jointly with friction estimator model. Experiments on simulated and field test data show that the learned friction estimator provides accurate estimates with robust uncertainty measures in a wide range of tire excitation levels. Meanwhile, the learned tire model reflects well-studied tire characteristics from field test data.
|
|
29. |
- Chen, Shuangshuang, 1992-, et al.
(författare)
-
Monte Carlo Filtering Objectives
- 2021
-
Ingår i: IJCAI International Joint Conference on Artificial Intelligence. - : International Joint Conferences on Artificial Intelligence. - 1045-0823. ; , s. 2256-2262
-
Konferensbidrag (refereegranskat)abstract
- Learning generative models and inferring latent trajectories have shown to be challenging for time series due to the intractable marginal likelihoods of flexible generative models. It can be addressed by surrogate objectives for optimization. We propose Monte Carlo filtering objectives (MCFOs), a family of variational objectives for jointly learning parametric generative models and amortized adaptive importance proposals of time series. MCFOs extend the choices of likelihood estimators beyond Sequential Monte Carlo in state-of-the-art objectives, possess important properties revealing the factors for the tightness of objectives, and allow for less biased and variant gradient estimates. We demonstrate that the proposed MCFOs and gradient estimations lead to efficient and stable model learning, and learned generative models well explain data and importance proposals are more sample efficient on various kinds of time series data.
|
|
30. |
- Chen, Xi, et al.
(författare)
-
Adversarial Feature Training for Generalizable Robotic Visuomotor Control
- 2020
-
Ingår i: 2020 International Conference on Robotics And Automation (ICRA). - : Institute of Electrical and Electronics Engineers (IEEE). ; , s. 1142-1148
-
Konferensbidrag (refereegranskat)abstract
- Deep reinforcement learning (RL) has enabled training action-selection policies, end-to-end, by learning a function which maps image pixels to action outputs. However, it's application to visuomotor robotic policy training has been limited because of the challenge of large-scale data collection when working with physical hardware. A suitable visuomotor policy should perform well not just for the task-setup it has been trained for, but also for all varieties of the task, including novel objects at different viewpoints surrounded by task-irrelevant objects. However, it is impractical for a robotic setup to sufficiently collect interactive samples in a RL framework to generalize well to novel aspects of a task.In this work, we demonstrate that by using adversarial training for domain transfer, it is possible to train visuomotor policies based on RL frameworks, and then transfer the acquired policy to other novel task domains. We propose to leverage the deep RL capabilities to learn complex visuomotor skills for uncomplicated task setups, and then exploit transfer learning to generalize to new task domains provided only still images of the task in the target domain. We evaluate our method on two real robotic tasks, picking and pouring, and compare it to a number of prior works, demonstrating its superiority.
|
|
31. |
- Chen, Xi, et al.
(författare)
-
Deep Reinforcement Learning to Acquire Navigation Skills for Wheel-Legged Robots in Complex Environments
- 2018
-
Ingår i: 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). - : Institute of Electrical and Electronics Engineers (IEEE). - 9781538680940
-
Konferensbidrag (refereegranskat)abstract
- Mobile robot navigation in complex and dynamic environments is a challenging but important problem. Reinforcement learning approaches fail to solve these tasks efficiently due to reward sparsities, temporal complexities and high-dimensionality of sensorimotor spaces which are inherent in such problems. We present a novel approach to train action policies to acquire navigation skills for wheel-legged robots using deep reinforcement learning. The policy maps height-map image observations to motor commands to navigate to a target position while avoiding obstacles. We propose to acquire the multifaceted navigation skill by learning and exploiting a number of manageable navigation behaviors. We also introduce a domain randomization technique to improve the versatility of the training samples. We demonstrate experimentally a significant improvement in terms of data-efficiency, success rate, robustness against irrelevant sensory data, and also the quality of the maneuver skills.
|
|
32. |
- Chen, Xi, et al.
(författare)
-
Meta-Learning for Multi-objective Reinforcement Learning
- 2019
-
Ingår i: Proceedings 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2019. - : Institute of Electrical and Electronics Engineers (IEEE). ; , s. 977-983
-
Konferensbidrag (refereegranskat)abstract
- Multi-objective reinforcement learning (MORL) is the generalization of standard reinforcement learning (RL) approaches to solve sequential decision making problems that consist of several, possibly conflicting, objectives. Generally, in such formulations, there is no single optimal policy which optimizes all the objectives simultaneously, and instead, a number of policies has to be found each optimizing a preference of the objectives. In this paper, we introduce a novel MORL approach by training a meta-policy, a policy simultaneously trained with multiple tasks sampled from a task distribution, for a number of randomly sampled Markov decision processes (MDPs). In other words, the MORL is framed as a meta-learning problem, with the task distribution given by a distribution over the preferences. We demonstrate that such a formulation results in a better approximation of the Pareto optimal solutions in terms of both the optimality and the computational efficiency. We evaluated our method on obtaining Pareto optimal policies using a number of continuous control problems with high degrees of freedom.
|
|
33. |
- Czeszumski, Artur, et al.
(författare)
-
Coordinating With a Robot Partner Affects Neural Processing Related to Action Monitoring
- 2021
-
Ingår i: Frontiers in Neurorobotics. - : Frontiers Media SA. - 1662-5218. ; 15
-
Tidskriftsartikel (refereegranskat)abstract
- Robots start to play a role in our social landscape, and they are progressively becoming responsive, both physically and socially. It begs the question of how humans react to and interact with robots in a coordinated manner and what the neural underpinnings of such behavior are. This exploratory study aims to understand the differences in human-human and human-robot interactions at a behavioral level and from a neurophysiological perspective. For this purpose, we adapted a collaborative dynamical paradigm from the literature. We asked 12 participants to hold two corners of a tablet while collaboratively guiding a ball around a circular track either with another participant or a robot. In irregular intervals, the ball was perturbed outward creating an artificial error in the behavior, which required corrective measures to return to the circular track again. Concurrently, we recorded electroencephalography (EEG). In the behavioral data, we found an increased velocity and positional error of the ball from the track in the human-human condition vs. human-robot condition. For the EEG data, we computed event-related potentials. We found a significant difference between human and robot partners driven by significant clusters at fronto-central electrodes. The amplitudes were stronger with a robot partner, suggesting a different neural processing. All in all, our exploratory study suggests that coordinating with robots affects action monitoring related processing. In the investigated paradigm, human participants treat errors during human-robot interaction differently from those made during interactions with other humans. These results can improve communication between humans and robot with the use of neural activity in real-time.
|
|
34. |
|
|
35. |
- Demir Kanik, Sumeyra Ummuhan, PhD, et al.
(författare)
-
Improving EEG-based Motor Execution Classification for Robot Control
- 2022
-
Ingår i: Proceedings 14th International Conference, SCSM 2022, Held as Part of the 24th HCI International Conference, HCII 2022. - Cham : Springer Nature. ; , s. 65-82
-
Konferensbidrag (refereegranskat)abstract
- Brain Computer Interface (BCI) systems have the potential to provide a communication tool using non-invasive signals which can be applied to various fields including neuro-rehabilitation and entertainment. Interpreting multi-class movement intentions in a real time setting to control external devices such as robotic arms remains to be one of the main challenges in the BCI field. We propose a learning framework to decode upper limb movement intentions before and during the movement execution (ME) with the inclusion of motor imagery (MI) trials. The design of the framework allows the system to evaluate the uncertainty of the classification output and respond accordingly. The EEG signals collected during MI and ME trials are fed into a hybrid architecture consisting of Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) with limited pre-processing. Outcome of the proposed approach shows the potential to anticipate the intended movement direction before the onset of the movement, while waiting to reach a certainty level by potentially observing more EEG data from the beginning of the actual movement before sending control commands to the robot to avoid undesired outcomes. Presented results indicate that both the accuracy and the confidence level of the model improves with the introduction of MI trials right before the movement execution. Our results confirm the possibility of the proposed model to contribute to real-time and continuous decoding of movement directions for robotic applications.
|
|
36. |
- Eklundh, Jan-Olof, 1939-, et al.
(författare)
-
Recognition of Objects in the Real World from a Systems Perspective
- 2005
-
Ingår i: Kuenstliche Intelligenz. - : Springer. - 0933-1875. ; 19:2, s. 12-17
-
Tidskriftsartikel (refereegranskat)abstract
- Based on a discussion of the requirements for a vision system operating in the real world we present a real-time system that includes a set of behaviours that makes it capable of handling a series of typical tasks. The system is able to localise objects of interests based on multiple cues, attend to the objects and finally recognise them while they are in fixation. A particular aspect of the system concerns the use of 3D cues. We end by showing the system running in practice and present results highlighting the merits of 3D-based attention and segmentation and multiple cues for recognition.
|
|
37. |
- Fu, Jia, et al.
(författare)
-
Component atention network for multimodal dance improvisation recognition
- 2023
-
Ingår i: PROCEEDINGS OF THE 25TH INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION, ICMI 2023. - : Association for Computing Machinery (ACM). ; , s. 114-118
-
Konferensbidrag (refereegranskat)abstract
- Dance improvisation is an active research topic in the arts. Motion analysis of improvised dance can be challenging due to its unique dynamics. Data-driven dance motion analysis, including recognition and generation, is often limited to skeletal data. However, data of other modalities, such as audio, can be recorded and benefit downstream tasks. This paper explores the application and performance of multimodal fusion methods for human motion recognition in the context of dance improvisation. We propose an attention-based model, component attention network (CANet), for multimodal fusion on three levels: 1) feature fusion with CANet, 2) model fusion with CANet and graph convolutional network (GCN), and 3) late fusion with a voting strategy. We conduct thorough experiments to analyze the impact of each modality in different fusion methods and distinguish critical temporal or component features. We show that our proposed model outperforms the two baseline methods, demonstrating its potential for analyzing improvisation in dance.
|
|
38. |
- Gamba, Matteo, et al.
(författare)
-
Are All Linear Regions Created Equal?
- 2022
-
Ingår i: Proceedings 25th International Conference on Artificial Intelligence and Statistics, AISTATS 2022. - : ML Research Press.
-
Konferensbidrag (refereegranskat)abstract
- The number of linear regions has been studied as a proxy of complexity for ReLU networks. However, the empirical success of network compression techniques like pruning and knowledge distillation, suggest that in the overparameterized setting, linear regions density might fail to capture the effective nonlinearity. In this work, we propose an efficient algorithm for discovering linear regions and use it to investigate the effectiveness of density in capturing the nonlinearity of trained VGGs and ResNets on CIFAR-10 and CIFAR-100. We contrast the results with a more principled nonlinearity measure based on function variation, highlighting the shortcomings of linear regions density. Furthermore, interestingly, our measure of nonlinearity clearly correlates with model-wise deep double descent, connecting reduced test error with reduced nonlinearity, and increased local similarity of linear regions.
|
|
39. |
- Gamba, Matteo, et al.
(författare)
-
Deep Double Descent via Smooth Interpolation
- 2023
-
Ingår i: Transactions on Machine Learning Research. - : Transactions on Machine Learning Research (TMLR). - 2835-8856. ; 4
-
Tidskriftsartikel (refereegranskat)abstract
- The ability of overparameterized deep networks to interpolate noisy data, while at the same time showing good generalization performance, has been recently characterized in terms of the double descent curve for the test error. Common intuition from polynomial regression suggests that overparameterized networks are able to sharply interpolate noisy data, without considerably deviating from the ground-truth signal, thus preserving generalization ability. At present, a precise characterization of the relationship between interpolation and generalization for deep networks is missing. In this work, we quantify sharpness of fit of the training data interpolated by neural network functions, by studying the loss landscape w.r.t. to the input variable locally to each training point, over volumes around cleanly- and noisily-labelled training samples, as we systematically increase the number of model parameters and training epochs. Our findings show that loss sharpness in the input space follows both model- and epoch-wise double descent, with worse peaks observed around noisy labels. While small interpolating models sharply fit both clean and noisy data, large interpolating models express a smooth loss landscape, where noisy targets are predicted over large volumes around training data points, in contrast to existing intuition.
|
|
40. |
- Gamba, Matteo, et al.
(författare)
-
On the geometry of rectifier convolutional neural networks
- 2019
-
Ingår i: Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019. - : Institute of Electrical and Electronics Engineers Inc.. - 9781728150239 ; , s. 793-797
-
Konferensbidrag (refereegranskat)abstract
- While recent studies have shed light on the expressivity, complexity and compositionality of convolutional networks, the real inductive bias of the family of functions reachable by gradient descent on natural data is still unknown. By exploiting symmetries in the preactivation space of convolutional layers, we present preliminary empirical evidence of regularities in the preimage of trained rectifier networks, in terms of arrangements of polytopes, and relate it to the nonlinear transformations applied by the network to its input.
|
|
41. |
- Gamba, Matteo, et al.
(författare)
-
On the Lipschitz Constant of Deep Networks and Double Descent
- 2023
-
Ingår i: Proceedings 34th British Machine Vision Conference 2023.
-
Konferensbidrag (refereegranskat)abstract
- Existing bounds on the generalization error of deep networks assume some form of smooth or bounded dependence on the input variable, falling short of investigating the mechanisms controlling such factors in practice. In this work, we present an extensive experimental study of the empirical Lipschitz constant of deep networks undergoing double descent, and highlight non-monotonic trends strongly correlating with the test error. Building a connection between parameter-space and input-space gradients for SGD around a critical point, we isolate two important factors - namely loss landscape curvature and distance of parameters from initialization - respectively controlling optimization dynamics around a critical point and bounding model function complexity, even beyond the training data. Our study presents novel insights on implicit regularization via overparameterization, and effective model complexity for networks trained in practice.
|
|
42. |
- Gandler, Gabriela Zarzar, et al.
(författare)
-
Object shape estimation and modeling, based on sparse Gaussian process implicit surfaces, combining visual data and tactile exploration
- 2020
-
Ingår i: Robotics and Autonomous Systems. - : ELSEVIER. - 0921-8890 .- 1872-793X. ; 126
-
Tidskriftsartikel (refereegranskat)abstract
- Inferring and representing three-dimensional shapes is an important part of robotic perception. However, it is challenging to build accurate models of novel objects based on real sensory data, because observed data is typically incomplete and noisy. Furthermore, imperfect sensory data suggests that uncertainty about shapes should be explicitly modeled during shape estimation. Such uncertainty models can usefully enable exploratory action planning for maximum information gain and efficient use of data. This paper presents a probabilistic approach for acquiring object models, based on visual and tactile data. We study Gaussian Process Implicit Surface (GPIS) representation. GPIS enables a non-parametric probabilistic reconstruction of object surfaces from 3D data points, while also providing a principled approach to encode the uncertainty associated with each region of the reconstruction. We investigate different configurations for GPIS, and interpret an object surface as the level-set of an underlying sparse GP. Experiments are performed on both synthetic data, and also real data sets obtained from two different robots physically interacting with objects. We evaluate performance by assessing how close the reconstructed surfaces are to ground-truth object models. We also evaluate how well objects from different categories are clustered, based on the reconstructed surface shapes. Results show that sparse GPs enable a reliable approximation to the full GP solution, and the proposed method yields adequate surface representations to distinguish objects. Additionally the presented approach is shown to provide computational efficiency, and also efficient use of the robot's exploratory actions.
|
|
43. |
|
|
44. |
- Ghadirzadeh, Ali, 1987-, et al.
(författare)
-
A Sensorimotor Approach for Self-Learning of Hand-Eye Coordination
- 2015
-
Ingår i: IEEE/RSJ International Conference onIntelligent Robots and Systems, Hamburg, September 28 - October 02, 2015. - : IEEE conference proceedings. - 9781479999941 ; , s. 4969-4975
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a sensorimotor contingencies (SMC) based method to fully autonomously learn to perform hand-eye coordination. We divide the task into two visuomotor subtasks, visual fixation and reaching, and implement these on a PR2 robot assuming no prior information on its kinematic model. Our contributions are three-fold: i) grounding a robot in the environment by exploiting SMCs in the action planning system, which eliminates the need for prior knowledge of the kinematic or dynamic models of the robot; ii) using a forward model to search for proper actions to solve the task by minimizing a cost function, instead of training a separate inverse model, to speed up training; iii) encoding 3D spatial positions of a target object based on the robot’s joint positions, thus avoiding calibration with respect to an external coordinate system. The method is capable of learning the task of hand-eye coordination from scratch by less than 20 sensory-motor pairs that are iteratively generated at real-time speed. In order to examine the robustness of the method while dealing with nonlinear image distortions, we apply a so-called retinal mapping image deformation to the input images. Experimental results show the successfulness of the method even under considerable image deformations.
|
|
45. |
- Ghadirzadeh, Ali, et al.
(författare)
-
A sensorimotor reinforcement learning framework for physical human-robot interaction
- 2016
-
Ingår i: IEEE International Conference on Intelligent Robots and Systems. - : IEEE. - 9781509037629 ; , s. 2682-2688
-
Konferensbidrag (refereegranskat)abstract
- Modeling of physical human-robot collaborations is generally a challenging problem due to the unpredictive nature of human behavior. To address this issue, we present a data-efficient reinforcement learning framework which enables a robot to learn how to collaborate with a human partner. The robot learns the task from its own sensorimotor experiences in an unsupervised manner. The uncertainty in the interaction is modeled using Gaussian processes (GP) to implement a forward model and an actionvalue function. Optimal action selection given the uncertain GP model is ensured by Bayesian optimization. We apply the framework to a scenario in which a human and a PR2 robot jointly control the ball position on a plank based on vision and force/torque data. Our experimental results show the suitability of the proposed method in terms of fast and data-efficient model learning, optimal action selection under uncertainty and equal role sharing between the partners.
|
|
46. |
- Ghadirzadeh, Ali, et al.
(författare)
-
Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- Reinforcement learning methods can achieve significant performance but require a large amount of training data collected on the same robotic platform. A policy trained with expensive data is rendered useless after making even a minor change to the robot hardware. In this paper, we address the challenging problem of adapting a policy, trained to perform a task, to a novel robotic hardware platform given only few demonstrations of robot motion trajectories on the target robot. We formulate it as a few-shot meta-learning problem where the goal is to find a meta-model that captures the common structure shared across different robotic platforms such that data-efficient adaptation can be performed. We achieve such adaptation by introducing a learning framework consisting of a probabilistic gradient-based meta-learning algorithm that models the uncertainty arising from the few-shot setting with a low-dimensional latent variable. We experimentally evaluate our framework on a simulated reaching and a real-robot picking task using 400 simulated robots generated by varying the physical parameters of an existing set of robotic platforms. Our results show that the proposed method can successfully adapt a trained policy to different robotic platforms with novel physical parameters and the superiority of our meta-learning algorithm compared to state-of-the-art methods for the introduced few-shot policy adaptation problem.
|
|
47. |
- Ghadirzadeh, Ali, et al.
(författare)
-
Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms
- 2021
-
Ingår i: 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). - : Institute of Electrical and Electronics Engineers (IEEE). ; , s. 1274-1280
-
Konferensbidrag (refereegranskat)abstract
- Reinforcement learning methods can achieve significant performance but require a large amount of training data collected on the same robotic platform. A policy trained with expensive data is rendered useless after making even a minor change to the robot hardware. In this paper, we address the challenging problem of adapting a policy, trained to perform a task, to a novel robotic hardware platform given only few demonstrations of robot motion trajectories on the target robot. We formulate it as a few-shot meta-learning problem where the goal is to find a meta-model that captures the common structure shared across different robotic platforms such that data-efficient adaptation can be performed. We achieve such adaptation by introducing a learning framework consisting of a probabilistic gradient-based meta-learning algorithm that models the uncertainty arising from the few-shot setting with a low-dimensional latent variable. We experimentally evaluate our framework on a simulated reaching and a real-robot picking task using 400 simulated robots generated by varying the physical parameters of an existing set of robotic platforms. Our results show that the proposed method can successfully adapt a trained policy to different robotic platforms with novel physical parameters and the superiority of our meta-learning algorithm compared to state-of-the-art methods for the introduced few-shot policy adaptation problem.
|
|
48. |
- Ghadirzadeh, Ali, et al.
(författare)
-
Deep predictive policy training using reinforcement learning
- 2017
-
Ingår i: 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2017. - : Institute of Electrical and Electronics Engineers (IEEE). - 9781538626825 ; , s. 2351-2358
-
Konferensbidrag (refereegranskat)abstract
- Skilled robot task learning is best implemented by predictive action policies due to the inherent latency of sensorimotor processes. However, training such predictive policies is challenging as it involves finding a trajectory of motor activations for the full duration of the action. We propose a data-efficient deep predictive policy training (DPPT) framework with a deep neural network policy architecture which maps an image observation to a sequence of motor activations. The architecture consists of three sub-networks referred to as the perception, policy and behavior super-layers. The perception and behavior super-layers force an abstraction of visual and motor data trained with synthetic and simulated training samples, respectively. The policy super-layer is a small subnetwork with fewer parameters that maps data in-between the abstracted manifolds. It is trained for each task using methods for policy search reinforcement learning. We demonstrate the suitability of the proposed architecture and learning framework by training predictive policies for skilled object grasping and ball throwing on a PR2 robot. The effectiveness of the method is illustrated by the fact that these tasks are trained using only about 180 real robot attempts with qualitative terminal rewards.
|
|
49. |
- Ghadirzadeh, Ali, et al.
(författare)
-
Human-Centered Collaborative Robots With Deep Reinforcement Learning
- 2021
-
Ingår i: IEEE Robotics and Automation Letters. - : Institute of Electrical and Electronics Engineers (IEEE). - 2377-3766. ; 6:2, s. 566-571
-
Tidskriftsartikel (refereegranskat)abstract
- We present a reinforcement learning based framework for human-centered collaborative systems. The framework is proactive and balances the benefits of timely actions with the risk of taking improper actions by minimizing the total time spent to complete the task. The framework is learned end-to-end in an unsupervised fashion addressing the perception uncertainties and decision making in an integrated manner. The framework is shown to provide more time-efficient coordination between human and robot partners on an example task of packaging compared to alternatives for which perception and decision-making systems are learned independently, using supervised learning. Two important benefits of the proposed approach are that tedious annotation of motion data is avoided, and the learning is performed on-line.
|
|
50. |
- Ghadirzadeh, Ali, et al.
(författare)
-
Learning visual forward models to compensate for self-induced image motion
- 2014
-
Ingår i: 23rd IEEE International Conference on Robot and Human Interactive Communication. - : IEEE. - 9781479967636 ; , s. 1110-1115
-
Konferensbidrag (refereegranskat)abstract
- Predicting the sensory consequences of an agent's own actions is considered an important skill for intelligent behavior. In terms of vision, so-called visual forward models can be applied to learn such predictions. This is no trivial task given the high-dimensionality of sensory data and complex action spaces. In this work, we propose to learn the visual consequences of changes in pan and tilt of a robotic head using a visual forward model based on Gaussian processes and SURF correspondences. This is done without any assumptions on the kinematics of the system or requirements on calibration. The proposed method is compared to an earlier work using accumulator-based correspondences and Radial Basis function networks. We also show the feasibility of the proposed method for detection of independent motion using a moving camera system. By comparing the predicted and actual captured images, image motion due to the robot's own actions and motion caused by moving external objects can be distinguished. Results show the proposed method to be preferable from the earlier method in terms of both prediction errors and ability to detect independent motion.
|
|