| 1. |
- Ivan, Jean-Paul A., 1995-, et al.
(författare)
-
Online Distance Field Priors for Gaussian Process Implicit Surfaces
- 2022
-
Ingår i: IEEE Robotics and Automation Letters. - : IEEE. - 2377-3766. ; 7:4, s. 8996-9003
-
Tidskriftsartikel (refereegranskat)abstract
- Gaussian process (GP) implicit surface models provide environment and object representations which elegantly address noise and uncertainty while remaining sufficiently flexible to capture complex geometry. However, GP models quickly become intractable as the size of the observation set grows-a trait which is difficult to reconcile with the rate at which modern range sensors produce data. Furthermore, naive applications of GPs to implicit surface models allocate model resources uniformly, thus using precious resources to capture simple geometry. In contrast to prior work addressing these challenges though model sparsification, spatial partitioning, or ad-hoc filtering, we propose introducing model bias online through the GP's mean function. We achieve more accurate distance fields using smaller models by creating a distance field prior from features which are easy to extract and have analytic distance fields. In particular, we demonstrate this approach using linear features. We show the proposed distance field halves model size in a 2D mapping task using data from a SICK S300 sensor. When applied to a single 3D scene from the TUM RGB-D SLAM dataset, we achieve a fivefold reduction in model size. Our proposed prior results in more accurate GP implicit surfaces, while allowing existing models to function in larger environments or with larger spatial partitions due to reduced model size.
|
|
| 2. |
- Arnekvist, Isac, 1986-, et al.
(författare)
-
Vpe : Variational policy embedding for transfer reinforcement learning
- 2019
-
Ingår i: 2019 International Conference on Robotics And Automation (ICRA). - : Institute of Electrical and Electronics Engineers (IEEE). - 9781538660263 - 9781538660270 ; , s. 36-42
-
Konferensbidrag (refereegranskat)abstract
- Reinforcement Learning methods are capable of solving complex problems, but resulting policies might perform poorly in environments that are even slightly different. In robotics especially, training and deployment conditions often vary and data collection is expensive, making retraining undesirable. Simulation training allows for feasible training times, but on the other hand suffer from a reality-gap when applied in real-world settings. This raises the need of efficient adaptation of policies acting in new environments. We consider the problem of transferring knowledge within a family of similar Markov decision processes. We assume that Q-functions are generated by some low-dimensional latent variable. Given such a Q-function, we can find a master policy that can adapt given different values of this latent variable. Our method learns both the generative mapping and an approximate posterior of the latent variables, enabling identification of policies for new tasks by searching only in the latent space, rather than the space of all policies. The low-dimensional space, and master policy found by our method enables policies to quickly adapt to new environments. We demonstrate the method on both a pendulum swing-up task in simulation, and for simulation-to-real transfer on a pushing task.
|
|
| 3. |
- Güler, Püren, et al.
(författare)
-
Visual state estimation in unseen environments through domain adaptation and metric learning
- 2022
-
Ingår i: Frontiers in Robotics and AI. - : Frontiers Media S.A.. - 2296-9144. ; 9
-
Tidskriftsartikel (refereegranskat)abstract
- In robotics, deep learning models are used in many visual perception applications, including the tracking, detection and pose estimation of robotic manipulators. The state of the art methods however are conditioned on the availability of annotated training data, which may in practice be costly or even impossible to collect. Domain augmentation is one popular method to improve generalization to out-of-domain data by extending the training data set with predefined sources of variation, unrelated to the primary task. While this typically results in better performance on the target domain, it is not always clear that the trained models are capable to accurately separate the signals relevant to solving the task (e.g., appearance of an object of interest) from those associated with differences between the domains (e.g., lighting conditions). In this work we propose to improve the generalization capabilities of models trained with domain augmentation by formulating a secondary structured metric-space learning objective. We concentrate on one particularly challenging domain transfer task-visual state estimation for an articulated underground mining machine-and demonstrate the benefits of imposing structure on the encoding space. Our results indicate that the proposed method has the potential to transfer feature embeddings learned on the source domain, through a suitably designed augmentation procedure, and on to an unseen target domain.
|
|
| 4. |
- Hang, Kaiyu, 1987-, et al.
(författare)
-
A Framework for Optimal Grasp Contact Planning
- 2017
-
Ingår i: IEEE Robotics and Automation Letters. - : IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC. - 2377-3766. ; 2:2, s. 704-711
-
Tidskriftsartikel (refereegranskat)abstract
- We consider the problem of finding grasp contacts that are optimal under a given grasp quality function on arbitrary objects. Our approach formulates a framework for contact-level grasping as a path finding problem in the space of supercontact grasps. The initial supercontact grasp contains all grasps and in each step along a path grasps are removed. For this, we introduce and formally characterize search space structure and cost functions underwhich minimal cost paths correspond to optimal grasps. Our formulation avoids expensive exhaustive search and reduces computational cost by several orders of magnitude. We present admissible heuristic functions and exploit approximate heuristic search to further reduce the computational cost while maintaining bounded suboptimality for resulting grasps. We exemplify our formulation with point-contact grasping for which we define domain specific heuristics and demonstrate optimality and bounded suboptimality by comparing against exhaustive and uniform cost search on example objects. Furthermore, we explain how to restrict the search graph to satisfy grasp constraints for modeling hand kinematics. We also analyze our algorithm empirically in terms of created and visited search states and resultant effective branching factor.
|
|
| 5. |
- Hang, Kaiyu, 1987-, et al.
(författare)
-
Hierarchical Fingertip Space : A Unified Framework for Grasp Planning and In-Hand Grasp Adaptation
- 2016
-
Ingår i: IEEE Transactions on robotics. - : IEEE Press. - 1552-3098 .- 1941-0468. ; 32:4, s. 960-972
-
Tidskriftsartikel (refereegranskat)abstract
- We present a unified framework for grasp planning and in-hand grasp adaptation using visual, tactile and proprioceptive feedback. The main objective of the proposed framework is to enable fingertip grasping by addressing problems of changed weight of the object, slippage and external disturbances. For this purpose, we introduce the Hierarchical Fingertip Space (HFTS) as a representation enabling optimization for both efficient grasp synthesis and online finger gaiting. Grasp synthesis is followed by a grasp adaptation step that consists of both grasp force adaptation through impedance control and regrasping/finger gaiting when the former is not sufficient. Experimental evaluation is conducted on an Allegro hand mounted on a Kuka LWR arm.
|
|
| 6. |
- Hang, Kaiyu, et al.
(författare)
-
Hierarchical Fingertip Space for Multi-fingered Precision Grasping
- 2014
-
Ingår i: 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, (IROS 2014). - : IEEE. - 9781479969340 ; , s. 1641-1648
-
Konferensbidrag (refereegranskat)abstract
- Dexterous in-hand manipulation of objects benefits from the ability of a robot system to generate precision grasps. In this paper, we propose a concept of Fingertip Space and its use for precision grasp synthesis. Fingertip Space is a representation that takes into account both the local geometry of object surface as well as the fingertip geometry. As such, it is directly applicable to the object point cloud data and it establishes a basis for the grasp search space. We propose a model for a hierarchical encoding of the Fingertip Space that enables multilevel refinement for efficient grasp synthesis. The proposed method works at the grasp contact level while not neglecting object shape nor hand kinematics. Experimental evaluation is performed for the Barrett hand considering also noisy and incomplete point cloud data.
|
|
| 7. |
- Haustein, Joshua Alexander, 1987-, et al.
(författare)
-
Learning Manipulation States and Actions for Efficient Non-prehensile Rearrangement Planning
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- This paper addresses non-prehensile rearrangement planning problems where a robot is tasked to rearrange objects among obstacles on a planar surface. We present an efficient planning algorithm that is designed to impose few assumptions on the robot's non-prehensile manipulation abilities and is simple to adapt to different robot embodiments. For this, we combine sampling-based motion planning with reinforcement learning and generative modeling. Our algorithm explores the composite configuration space of objects and robot as a search over robot actions, forward simulated in a physics model. This search is guided by a generative model that provides robot states from which an object can be transported towards a desired state, and a learned policy that provides corresponding robot actions. As an efficient generative model, we apply Generative Adversarial Networks. We implement and evaluate our approach for robots endowed with configuration spaces in SE(2). We demonstrate empirically the efficacy of our algorithm design choices and observe more than 2x speedup in planning time on various test scenarios compared to a state-of-the-art approach.
|
|
| 8. |
|
|
| 9. |
- Haustein, Joshua Alexander, 1987-, et al.
(författare)
-
Non-prehensile Rearrangement Planning with Learned Manipulation States and Actions
- 2018
-
Ingår i: Workshop on "Machine Learning in Robot Motion Planning" at the International Conference on Intelligent Robots and Systems (IROS) 2018.
-
Konferensbidrag (refereegranskat)abstract
- n this work we combine sampling-based motionplanning with reinforcement learning and generative modelingto solve non-prehensile rearrangement problems. Our algorithmexplores the composite configuration space of objects and robotas a search over robot actions, forward simulated in a physicsmodel. This search is guided by a generative model thatprovides robot states from which an object can be transportedtowards a desired state, and a learned policy that providescorresponding robot actions. As an efficient generative model,we apply Generative Adversarial Networks.
|
|
| 10. |
- Haustein, J A, et al.
(författare)
-
Object placement planning and optimization for robot manipulators
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- We address the problem of motion planning for a robotic manipulator with the task to place a grasped object in a cluttered environment. In this task, we need to locate a collision-free pose for the object that a) facilitates the stable placement of the object, b) is reachable by the robot manipulator and c) optimizes a user-given placement objective. Because of the placement objective, this problem is more challenging than classical motion planning where the target pose is defined from the start. To solve this task, we propose an anytime algorithm that integrates sampling-based motion planning for the robot manipulator with a novel hierarchical search for suitable placement poses. We evaluate our approach on a dual-arm robot for two different placement objectives, and observe its effectiveness even in challenging scenarios.
|
|
