1. |
- Billing, Erik, 1981-, et al.
(författare)
-
Behavior recognition for learning from demonstration
- 2010
-
Ingår i: 2010 IEEE International Conference on Robotics and Automation. - : IEEE. - 9781424450404 - 9781424450381 ; , s. 866-872
-
Konferensbidrag (refereegranskat)abstract
- Two methods for behavior recognition are presented and evaluated. Both methods are based on the dynamic temporal difference algorithm Predictive Sequence Learning (PSL) which has previously been proposed as a learning algorithm for robot control. One strength of the proposed recognition methods is that the model PSL builds to recognize behaviors is identical to that used for control, implying that the controller (inverse model) and the recognition algorithm (forward model) can be implemented as two aspects of the same model. The two proposed methods, PSLE-Comparison and PSLH-Comparison, are evaluated in a Learning from Demonstration setting, where each algorithm should recognize a known skill in a demonstration performed via teleoperation. PSLH-Comparison produced the smallest recognition error. The results indicate that PSLH-Comparison could be a suitable algorithm for integration in a hierarchical control system consistent with recent models of human perception and motor control.
|
|
2. |
- Billing, Erik, 1981-
(författare)
-
Cognition Rehearsed : Recognition and Reproduction of Demonstrated Behavior
- 2012
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The work presented in this dissertation investigates techniques for robot Learning from Demonstration (LFD). LFD is a well established approach where the robot is to learn from a set of demonstrations. The dissertation focuses on LFD where a human teacher demonstrates a behavior by controlling the robot via teleoperation. After demonstration, the robot should be able to reproduce the demonstrated behavior under varying conditions. In particular, the dissertation investigates techniques where previous behavioral knowledge is used as bias for generalization of demonstrations. The primary contribution of this work is the development and evaluation of a semi-reactive approach to LFD called Predictive Sequence Learning (PSL). PSL has many interesting properties applied as a learning algorithm for robots. Few assumptions are introduced and little task-specific configuration is needed. PSL can be seen as a variable-order Markov model that progressively builds up the ability to predict or simulate future sensory-motor events, given a history of past events. The knowledge base generated during learning can be used to control the robot, such that the demonstrated behavior is reproduced. The same knowledge base can also be used to recognize an on-going behavior by comparing predicted sensor states with actual observations. Behavior recognition is an important part of LFD, both as a way to communicate with the human user and as a technique that allows the robot to use previous knowledge as parts of new, more complex, controllers. In addition to the work on PSL, this dissertation provides a broad discussion on representation, recognition, and learning of robot behavior. LFD-related concepts such as demonstration, repetition, goal, and behavior are defined and analyzed, with focus on how bias is introduced by the use of behavior primitives. This analysis results in a formalism where LFD is described as transitions between information spaces. Assuming that the behavior recognition problem is partly solved, ways to deal with remaining ambiguities in the interpretation of a demonstration are proposed. The evaluation of PSL shows that the algorithm can efficiently learn and reproduce simple behaviors. The algorithm is able to generalize to previously unseen situations while maintaining the reactive properties of the system. As the complexity of the demonstrated behavior increases, knowledge of one part of the behavior sometimes interferes with knowledge of another parts. As a result, different situations with similar sensory-motor interactions are sometimes confused and the robot fails to reproduce the behavior. One way to handle these issues is to introduce a context layer that can support PSL by providing bias for predictions. Parts of the knowledge base that appear to fit the present context are highlighted, while other parts are inhibited. Which context should be active is continually re-evaluated using behavior recognition. This technique takes inspiration from several neurocomputational models that describe parts of the human brain as a hierarchical prediction system. With behavior recognition active, continually selecting the most suitable context for the present situation, the problem of knowledge interference is significantly reduced and the robot can successfully reproduce also more complex behaviors.
|
|
3. |
- Billing, Erik, 1981-
(författare)
-
Cognition reversed : Robot learning from demonstration
- 2009
-
Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The work presented in this thesis investigates techniques for learning from demonstration (LFD). LFD is a well established approach to robot learning, where a teacher demonstrates a behavior to a robot pupil. This thesis focuses on LFD where a human teacher demonstrates a behavior by controlling the robot via teleoperation. The robot should after demonstration be able to execute the demonstrated behavior under varying conditions. Several views on representation, recognition and learning of robot behavior are presented and discussed from a cognitive and computational perspective. LFD-related concepts such as behavior, goal, demonstration, and repetition are defined and analyzed, with focus on how bias is introduced by the use of behavior primitives. This analysis results in a formalism where LFD is described as transitions between information spaces. Assuming that the behavior recognition problem is partly solved, ways to deal with remaining ambiguities in the interpretation of a demonstration are proposed. A total of five algorithms for behavior recognition are proposed and evaluated, including the dynamic temporal difference algorithm Predictive Sequence Learning (PSL). PSL is model-free in the sense that it makes few assumptions of what is to be learned. One strength of PSL is that it can be used for both robot control and recognition of behavior. While many methods for behavior recognition are concerned with identifying invariants within a set of demonstrations, PSL takes a different approach by using purely predictive measures. This may be one way to reduce the need for bias in learning. PSL is, in its current form, subjected to combinatorial explosion as the input space grows, which makes it necessary to introduce some higher level coordination for learning of complex behaviors in real-world robots. The thesis also gives a broad introduction to computational models of the human brain, where a tight coupling between perception and action plays a central role. With the focus on generation of bias, typical features of existing attempts to explain humans' and other animals' ability to learn are presented and analyzed, from both a neurological and an information theoretic perspective. Based on this analysis, four requirements for implementing general learning ability in robots are proposed. These requirements provide guidance to how a coordinating structure around PSL and similar algorithms should be implemented in a model-free way.
|
|
4. |
- Billing, Erik, 1981-, et al.
(författare)
-
Model-free learning from demonstration
- 2010
-
Ingår i: ICAART 2010 - Proceedings of the international conference on agents and artificial intelligence. - Portugal : INSTICC. - 9789896740221 ; , s. 62-71
-
Konferensbidrag (refereegranskat)abstract
- A novel robot learning algorithm called Predictive Sequence Learning (PSL) is presented and evaluated. PSL is a model-free prediction algorithm inspired by the dynamic temporal difference algorithm S-Learning. While S-Learning has previously been applied as a reinforcement learning algorithm for robots, PSL is here applied to a Learning from Demonstration problem. The proposed algorithm is evaluated on four tasks using a Khepera II robot. PSL builds a model from demonstrated data which is used to repeat the demonstrated behavior. After training, PSL can control the robot by continually predicting the next action, based on the sequence of passed sensor and motor events. PSL was able to successfully learn and repeat the first three (elementary) tasks, but it was unable to successfully repeat the fourth (composed) behavior. The results indicate that PSL is suitable for learning problems up to a certain complexity, while higher level coordination is required for learning more complex behaviors.
|
|
5. |
- Billing, Erik, 1981-, et al.
(författare)
-
Predictive learning from demonstration
- 2011. - 1
-
Ingår i: Agents and artificial Intelligence. - Berlin : Springer Verlag. - 9783642198892 - 9783642198908 ; , s. 186-200
-
Bokkapitel (refereegranskat)abstract
- A model-free learning algorithm called Predictive Sequence Learning (PSL) is presented and evaluated in a robot Learning from Demonstration (LFD) setting. PSL is inspired by several functional models of the brain. It constructs sequences of predictable sensory-motor patterns, without relying on predefined higher-level concepts. The algorithm is demonstrated on a Khepera II robot in four different tasks. During training, PSL generates a hypothesis library from demonstrated data. The library is then used to control the robot by continually predicting the next action, based on the sequence of passed sensor and motor events. In this way, the robot reproduces the demonstrated behavior. PSL is able to successfully learn and repeat three elementary tasks, but is unable to repeat a fourth, composed behavior. The results indicate that PSL is suitable for learning problems up to a certain complexity, while higher level coordination is required for learning more complex behaviors.
|
|
6. |
- Billing, Erik, 1981-, et al.
(författare)
-
Robot learning from demonstration using predictive sequence learning
- 2012
-
Ingår i: Robotic systems. - Kanpur, India : IN-TECH. - 9789533079417 ; , s. 235-250
-
Bokkapitel (refereegranskat)abstract
- In this chapter, the prediction algorithm Predictive Sequence Learning (PSL) is presented and evaluated in a robot Learning from Demonstration (LFD) setting. PSL generates hypotheses from a sequence of sensory-motor events. Generated hypotheses can be used as a semi-reactive controller for robots. PSL has previously been used as a method for LFD, but suffered from combinatorial explosion when applied to data with many dimensions, such as high dimensional sensor and motor data. A new version of PSL, referred to as Fuzzy Predictive Sequence Learning (FPSL), is presented and evaluated in this chapter. FPSL is implemented as a Fuzzy Logic rule base and works on a continuous state space, in contrast to the discrete state space used in the original design of PSL. The evaluation of FPSL shows a significant performance improvement in comparison to the discrete version of the algorithm. Applied to an LFD task in a simulated apartment environment, the robot is able to learn to navigate to a specific location, starting from an unknown position in the apartment.
|
|
7. |
- Billing, Erik, 1981-, et al.
(författare)
-
Robot learning from demonstration using predictive sequence learning
- 2011
-
Ingår i: Robotic systems. - Kanpur, India : IN-TECH. - 9789533079417 ; , s. 235-250
-
Bokkapitel (refereegranskat)abstract
- In this chapter, the prediction algorithm Predictive Sequence Learning (PSL) is presented and evaluated in a robot Learning from Demonstration (LFD) setting. PSL generates hypotheses from a sequence of sensory-motor events. Generated hypotheses can be used as a semi-reactive controller for robots. PSL has previously been used as a method for LFD, but suffered from combinatorial explosion when applied to data with many dimensions, such as high dimensional sensor and motor data. A new version of PSL, referred to as Fuzzy Predictive Sequence Learning (FPSL), is presented and evaluated in this chapter. FPSL is implemented as a Fuzzy Logic rule base and works on a continuous state space, in contrast to the discrete state space used in the original design of PSL. The evaluation of FPSL shows a significant performance improvement in comparison to the discrete version of the algorithm. Applied to an LFD task in a simulated apartment environment, the robot is able to learn to navigate to a specific location, starting from an unknown position in the apartment.
|
|
8. |
- Billing, Erik, 1981-, et al.
(författare)
-
Simultaneous control and recognition of demonstrated behavior
- 2011
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- A method for Learning from Demonstration (LFD) is presented and evaluated on a simulated Robosoft Kompai robot. The presented algorithm, called Predictive Sequence Learning (PSL), builds fuzzy rules describing temporal relations between sensory-motor events recorded while a human operator is tele-operating the robot. The generated rule base can be used to control the robot and to predict expected sensor events in response to executed actions. The rule base can be trained under different contexts, represented as fuzzy sets. In the present work, contexts are used to represent different behaviors. Several behaviors can in this way be stored in the same rule base and partly share information. The context that best matches present circumstances can be identified using the predictive model and the robot can in this way automatically identify the most suitable behavior for precent circumstances. The performance of PSL as a method for LFD is evaluated with, and without, contextual information. The results indicate that PSL without contexts can learn and reproduce simple behaviors. The system also successfully identifies the most suitable context in almost all test cases. The robot's ability to reproduce more complex behaviors, with partly overlapping and conflicting information, significantly increases with the use of contexts. The results support a further development of PSL as a component of a dynamic hierarchical system performing control and predictions on several levels of abstraction.
|
|
9. |
- Billing, Erik, 1981-, et al.
(författare)
-
Simultaneous recognition and reproduction of demonstrated behavior
- 2015
-
Ingår i: Biologically Inspired Cognitive Architectures. - : Elsevier. - 2212-683X. ; 12, s. 43-53
-
Tidskriftsartikel (refereegranskat)abstract
- Predictions of sensory-motor interactions with the world is often referred to as a key component in cognition. We here demonstrate that prediction of sensory-motor events, i.e., relationships between percepts and actions, is sufficient to learn navigation skills for a robot navigating in an apartment environment. In the evaluated application, the simulated Robosoft Kompai robot learns from human demonstrations. The system builds fuzzy rules describing temporal relations between sensory-motor events recorded while a human operator is tele-operating the robot. With this architecture, referred to as Predictive Sequence Learning (PSL), learned associations can be used to control the robot and to predict expected sensor events in response to executed actions. The predictive component of PSL is used in two ways: 1) to identify which behavior that best matches current context and 2) to decide when to learn, i.e., update the confidence of different sensory-motor associations. Using this approach, knowledge interference due to over-fitting of an increasingly complex world model can be avoided. The system can also automatically estimate the confidence in the currently executed behavior and decide when to switch to an alternate behavior. The performance of PSL as a method for learning from demonstration is evaluated with, and without, contextual information. The results indicate that PSL without contextual information can learn and reproduce simple behaviors, but fails when the behavioral repertoire becomes more diverse. When a contextual layer is added, PSL successfully identifies the most suitable behavior in almost all test cases. The robot's ability to reproduce more complex behaviors, with partly overlapping and conflicting information, significantly increases with the use of contextual information. The results support a further development of PSL as a component of a dynamic hierarchical system performing control and predictions on several levels of abstraction.
|
|
10. |
- Hanson, Lars, et al.
(författare)
-
Current Trends in Research and Application of Digital Human Modeling
- 2022
-
Ingår i: Proceedings of the 21st Congress of the International Ergonomics Association (IEA 2021). - Cham : Springer. - 9783030746131 - 9783030746148 ; , s. 358-366
-
Konferensbidrag (refereegranskat)abstract
- The paper reports an investigation conducted during the DHM2020 Symposium regarding current trends in research and application of DHM in academia, software development, and industry. The results show that virtual reality (VR), augmented reality (AR), and digital twin are major current trends. Furthermore, results show that human diversity is considered in DHM using established methods. Results also show a shift from the assessment of static postures to assessment of sequences of actions, combined with a focus mainly on human well-being and only partly on system performance. Motion capture and motion algorithms are alternative technologies introduced to facilitate and improve DHM simulations. Results from the DHM simulations are mainly presented through pictures or animations.
|
|
11. |
- Alenljung, Beatrice, 1971-, et al.
(författare)
-
Conveying Emotions by Touch to the Nao Robot : A User Experience Perspective
- 2018
-
Ingår i: Multimodal Technologies and Interaction. - : MDPI. - 2414-4088. ; 2:4
-
Tidskriftsartikel (refereegranskat)abstract
- Social robots are expected gradually to be used by more and more people in a widerrange of settings, domestic as well as professional. As a consequence, the features and qualityrequirements on human–robot interaction will increase, comprising possibilities to communicateemotions, establishing a positive user experience, e.g., using touch. In this paper, the focus is ondepicting how humans, as the users of robots, experience tactile emotional communication with theNao Robot, as well as identifying aspects affecting the experience and touch behavior. A qualitativeinvestigation was conducted as part of a larger experiment. The major findings consist of 15 differentaspects that vary along one or more dimensions and how those influence the four dimensions ofuser experience that are present in the study, as well as the different parts of touch behavior ofconveying emotions.
|
|
12. |
- Alenljung, Beatrice, et al.
(författare)
-
User Experience of Conveying Emotions by Touch
- 2017
-
Ingår i: Proceedings of the 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN). - : IEEE. - 9781538635179 - 9781538635193 - 9781538635186 ; , s. 1240-1247
-
Konferensbidrag (refereegranskat)abstract
- In the present study, 64 users were asked to convey eight distinct emotion to a humanoid Nao robot via touch, and were then asked to evaluate their experiences of performing that task. Large differences between emotions were revealed. Users perceived conveying of positive/pro-social emotions as significantly easier than negative emotions, with love and disgust as the two extremes. When asked whether they would act differently towards a human, compared to the robot, the users’ replies varied. A content analysis of interviews revealed a generally positive user experience (UX) while interacting with the robot, but users also found the task challenging in several ways. Three major themes with impact on the UX emerged; responsiveness, robustness, and trickiness. The results are discussed in relation to a study of human-human affective tactile interaction, with implications for human-robot interaction (HRI) and design of social and affective robotics in particular.
|
|
13. |
- Andreasson, Rebecca, et al.
(författare)
-
Affective Touch in Human-Robot Interaction: Conveying Emotion to the Nao Robot
- 2018
-
Ingår i: International Journal of Social Robotics. - : Springer Science and Business Media LLC. - 1875-4791 .- 1875-4805. ; 10:4, s. 473-491
-
Tidskriftsartikel (refereegranskat)abstract
- Affective touch has a fundamental role in human development, social bonding, and for providing emotional support in interpersonal relationships. We present, what is to our knowledge, the first HRI study of tactile conveyance of both positive and negative emotions (affective touch) on the Nao robot, and based on an experimental set-up from a study of human-human tactile communication. In the present work, participants conveyed eight emotions to a small humanoid robot via touch. We found that female participants conveyed emotions for a longer time, using more varied interaction and touching more regions on the robot's body, compared to male participants. Several differences between emotions were found such that emotions could be classified by the valence of the emotion conveyed, by combining touch amount and duration. Overall, these results show high agreement with those reported for human-human affective tactile communication and could also have impact on the design and placement of tactile sensors on humanoid robots.
|
|
14. |
- Billing, Erik, 1981-, et al.
(författare)
-
A formalism for learning from demonstration
- 2010
-
Ingår i: Paladyn - Journal of Behavioral Robotics. - : De Gruyter Open. - 2080-9778 .- 2081-4836. ; 1:1, s. 1-13
-
Tidskriftsartikel (refereegranskat)abstract
- The paper describes and formalizes the concepts and assumptions involved in Learning from Demonstration (LFD), a common learning technique used in robotics. LFD-related concepts like goal, generalization, and repetition are here defined, analyzed, and put into context. Robot behaviors are described in terms of trajectories through information spaces and learning is formulated as mappings between some of these spaces. Finally, behavior primitives are introduced as one example of good bias in learning, dividing the learning process into the three stages of behavior segmentation, behavior recognition, and behavior coordination. The formalism is exemplified through a sequence learning task where a robot equipped with a gripper arm is to move objects to specific areas. The introduced concepts are illustrated with special focus on how bias of various kinds can be used to enable learning from a single demonstration, and how ambiguities in demonstrations can be identified and handled.
|
|
15. |
- Billing, Erik, 1981-
(författare)
-
A New Look at Habits using Simulation Theory
- 2017
-
Ingår i: Proceedings of the Digitalisation for a Sustainable Society. - Göteborg, Sweden.
-
Konferensbidrag (refereegranskat)abstract
- Habits as a form of behavior re-execution without explicit deliberation is discussed in terms of implicit anticipation, to be contrasted with explicit anticipation and mental simulation. Two hypotheses, addressing how habits and mental simulation may be implemented in the brain and to what degree they represent two modes brain function, are formulated. Arguments for and against the two hypotheses are discussed shortly, specifically addressing whether habits and mental simulation represent two distinct functions, or to what degree there may be intermediate forms of habit execution involving partial deliberation. A potential role of habits in memory consolidation is also hypnotized.
|
|
16. |
- Billing, Erik, PhD, 1981-, et al.
(författare)
-
Automatic Selection of Viewpoint for Digital Human Modelling
- 2020
-
Ingår i: DHM2020. - Amsterdam : IOS Press. - 9781643681047 - 9781643681054 ; , s. 61-70
-
Konferensbidrag (refereegranskat)abstract
- During concept design of new vehicles, work places, and other complex artifacts, it is critical to assess positioning of instruments and regulators from the perspective of the end user. One common way to do these kinds of assessments during early product development is by the use of Digital Human Modelling (DHM). DHM tools are able to produce detailed simulations, including vision. Many of these tools comprise evaluations of direct vision and some tools are also able to assess other perceptual features. However, to our knowledge, all DHM tools available today require manual selection of manikin viewpoint. This can be both cumbersome and difficult, and requires that the DHM user possesses detailed knowledge about visual behavior of the workers in the task being modelled. In the present study, we take the first steps towards an automatic selection of viewpoint through a computational model of eye-hand coordination. We here report descriptive statistics on visual behavior in a pick-and-place task executed in virtual reality. During reaching actions, results reveal a very high degree of eye-gaze towards the target object. Participants look at the target object at least once during basically every trial, even during a repetitive action. The object remains focused during large proportions of the reaching action, even when participants are forced to move in order to reach the object. These results are in line with previous research on eye-hand coordination and suggest that DHM tools should, by default, set the viewpoint to match the manikin’s grasping location.
|
|
17. |
- Billing, Erik, 1981-, et al.
(författare)
-
Behavior recognition for segmentation of demonstrated tasks
- 2008
-
Ingår i: IEEE SMC International Conference on Distributed Human-Machine Systems (DHMS). - 9788001040270
-
Konferensbidrag (refereegranskat)abstract
- One common approach to the robot learning technique Learning From Demonstration, is to use a set of pre-programmed skills as building blocks for more complex tasks. One important part of this approach is recognition of these skills in a demonstration comprising a stream of sensor and actuator data. In this paper, three novel techniques for behavior recognition are presented and compared. The first technique is function-oriented and compares actions for similar inputs. The second technique is based on auto-associative neural networks and compares reconstruction errors in sensory-motor space. The third technique is based on S-Learning and compares sequences of patterns in sensory-motor space. All three techniques compute an activity level which can be seen as an alternative to a pure classification approach. Performed tests show how the former approach allows a more informative interpretation of a demonstration, by not determining "correct" behaviors but rather a number of alternative interpretations.
|
|
18. |
- Billing, Erik, 1981-
(författare)
-
Cognitive Perspectives on Robot Behavior
- 2010
-
Ingår i: Proceedings of the 2nd International Conference on Agents and Artificial Intelligence. - Portugal : INSTICC. - 9789896740214 ; , s. 373-382, s. 373-382
-
Konferensbidrag (refereegranskat)abstract
- A growing body of research within the field of intelligent robotics argues for a view of intelligence drastically different from classical artificial intelligence and cognitive science. The holistic and embodied ideas expressed by this research promote the view that intelligence is an emergent phenomenon. Similar perspectives, where numerous interactions within the system lead to emergent properties and cognitive abilities beyond that of the individual parts, can be found within many scientific fields. With the goal of understanding how behavior may be represented in robots, the present review tries to grasp what this notion of emergence really means and compare it with a selection of theories developed for analysis of human cognition, including the extended mind, distributed cognition and situated action. These theories reveal a view of intelligence where common notions of objects, goals, language and reasoning have to be rethought. A view where behavior, as well as the agent as such, is defined by the observer rather than given by their nature. Structures in the environment emerge by interaction rather than recognized. In such a view, the fundamental question is how emergent systems appear and develop, and how they may be controlled.
|
|
19. |
- Billing, Erik, 1981-, et al.
(författare)
-
Digital Human Modelling in Action
- 2019
-
Ingår i: Proceedings of the 15th SweCog Conference. - Skövde : University of Skövde. - 9789198366754 ; , s. 25-28
-
Konferensbidrag (refereegranskat)
|
|
20. |
- Billing, Erik, 1981-, et al.
(författare)
-
Expectations of robot technology in welfare
- 2019
-
Konferensbidrag (refereegranskat)abstract
- We report findings from a survey on expectations of robot technology in welfare, within the coming 20 years. 34 assistant nurses answered a questionnaire on which tasks, from their daily work, that they believe robots can perform, already today or in the near future. Additionally, the Negative attitudes toward robots scale (NARS) was used to estimate participants' attitudes towards robots in general. Results reveal high expectations of robots, where at least half of the participants answered Already today or Within 10 years to 9 out of 10 investigated tasks. Participants were also fairly positive towards robots, reporting low scores on NARS. The obtained results can be interpreted as a serious over-estimation of what robots will be able to do in the near future, but also large varieties in participants' interpretation of what robots are. We identify challenges in communicating both excitement towards a technology in rapid development and realistic limitations of this technology.
|
|
21. |
- Billing, Erik, 1981-, et al.
(författare)
-
Finding Your Way from the Bed to the Kitchen: Reenacting and Recombining Sensorimotor Episodes Learned from Human Demonstration
- 2016
-
Ingår i: Frontiers in Robotics and Ai. - Lausanne, Switzerland : Frontiers Media SA. - 2296-9144. ; 3
-
Tidskriftsartikel (refereegranskat)abstract
- Several simulation theories have been proposed as an explanation for how humans and other agents internalize an "inner world" that allows them to simulate interactions with the external real world - prospectively and retrospectively. Such internal simulation of interaction with the environment has been argued to be a key mechanism behind mentalizing and planning. In the present work, we study internal simulations in a robot acting in a simulated human environment. A model of sensory-motor interactions with the environment is generated from human demonstrations and tested on a Robosoft Kompai robot. The model is used as a controller for the robot, reproducing the demonstrated behavior. Information from several different demonstrations is mixed, allowing the robot to produce novel paths through the environment, toward a goal specified by top-down contextual information. The robot model is also used in a covert mode, where the execution of actions is inhibited and perceptions are generated by a forward model. As a result, the robot generates an internal simulation of the sensory-motor interactions with the environment. Similar to the overt mode, the model is able to reproduce the demonstrated behavior as internal simulations. When experiences from several demonstrations are combined with a top-down goal signal, the system produces internal simulations of novel paths through the environment. These results can be understood as the robot imagining an "inner world" generated from previous experience, allowing it to try out different possible futures without executing actions overtly. We found that the success rate in terms of reaching the specified goal was higher during internal simulation, compared to overt action. These results are linked to a reduction in prediction errors generated during covert action. Despite the fact that the model is quite successful in terms of generating covert behavior toward specified goals, internal simulations display different temporal distributions compared to their overt counterparts. Links to human cognition and specifically mental imagery are discussed.
|
|
22. |
- Billing, Erik, 1981-, et al.
(författare)
-
Formalising learning from demonstration
- 2008
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- The paper describes and formalizes the concepts and assumptions involved in Learning from Demonstration (LFD), a common learning technique used in robotics. Inspired by the work on planning and actuation by LaValle, common LFD-related concepts like goal, generalization, and repetition are here defined, analyzed, and put into context. Robot behaviors are described in terms of trajectories through information spaces and learning is formulated as the mappings between some of these spaces. Finally, behavior primitives are introduced as one example of useful bias in the learning process, dividing the learning process into the three stages of behavior segmentation, behavior recognition, and behavior coordination.
|
|
23. |
- Billing, Erik, PhD, 1981-, et al.
(författare)
-
Language Models for Human-Robot Interaction
- 2023
-
Ingår i: HRI '23. - New York, NY, USA : ACM Digital Library. - 9781450399708 ; , s. 905-906
-
Konferensbidrag (refereegranskat)abstract
- Recent advances in large scale language models have significantly changed the landscape of automatic dialogue systems and chatbots. We believe that these models also have a great potential for changing the way we interact with robots. Here, we present the first integration of the OpenAI GPT-3 language model for the Aldebaran Pepper and Nao robots. The present work transforms the text-based API of GPT-3 into an open verbal dialogue with the robots. The system will be presented live during the HRI2023 conference and the source code of this integration is shared with the hope that it will serve the community in designing and evaluating new dialogue systems for robots.
|
|
24. |
- Billing, Erik, 1981-, et al.
(författare)
-
Modeling the Interplay between Conditioning and Attention in a Humanoid Robot : Habituation and Attentional Blocking
- 2014
-
Ingår i: IEEE ICDL-EPIROB 2014. - : IEEE conference proceedings. - 9781479975402 ; , s. 41-47
-
Konferensbidrag (refereegranskat)abstract
- A novel model of role of conditioning in attention is presented and evaluated on a Nao humanoid robot. The model implements conditioning and habituation in interaction with a dynamic neural field where different stimuli compete for activation. The model can be seen as a demonstration of how stimulus-selection and action-selection can be combined and illustrates how positive or negative reinforcement have different effects on attention and action. Attention is directed toward both rewarding and punishing stimuli, but appetitive actions are only directed toward positive stimuli. We present experiments where the model is used to control a Nao robot in a task where it can select between two objects. The model demonstrates some emergent effects also observed in similar experiments with humans and animals, including attentional blocking and latent inhibition.
|
|
25. |
|
|