Perceiving the unusual: Temporal properties of hierarchical motor representations for action perception

Demiris, Yiannis; Simmons, Gavin

doi:10.1016/j.neunet.2006.02.005

Cited by 26 publications

(20 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An increased interest in learning algorithms that will equip robots to learn by imitation of actions from both humans and other robotic agents has resulted in many research directions within the area. To address issues concerning attention and perception, a hierarchical model was presented in [2]. For methodologies to teach robots to learn new skills, while Muench et al proposed to ask the demonstrators explicit questions in order to generalise an action [3], some others made use of reinforcement learning to extract useful information ( [4], [5]).…”

Section: Introductionmentioning

confidence: 99%

Efficient template-based path imitation by invariant feature mapping

Demiris

2009

2009 IEEE International Conference on Robotics and Biomimetics (ROBIO)

Self Cite

View full text Add to dashboard Cite

Abstract-We propose a novel approach for robot movement imitation that is suitable for robotic arm movement in tasks such as reaching and grasping. This algorithm selects a previously observed path demonstrated by an agent and generates a path in a novel situation based on pairwise mapping of invariant feature locations present in both the demonstrated and the new scenes using minimum distortion and minimum energy strategies. This One-Shot Learning algorithm is capable of not only mapping simple pointto-point paths but also adapting to more complex tasks such as involvement of forced waypoints. As compared to traditional methodologies, our work does not require extensive training for generalisation as well as expensive run-time computation for accuracy. Cross-validation statistics of grasping experiments show great similarity between the paths produced by human subjects and the proposed algorithm.

show abstract

Section: Introductionmentioning

confidence: 99%

Efficient template-based path imitation by invariant feature mapping

Demiris

2009

2009 IEEE International Conference on Robotics and Biomimetics (ROBIO)

Self Cite

View full text Add to dashboard Cite

show abstract

“…This is particularly evident in this model, which actually employs the simulated position to drive attention, whilst in previous models prediction was used to modulate bottom-up attention (see e.g. [6]). Experimental results have confirmed the advantages of the attention-based action recognition system, both in terms of precision and, maybe more importantly, in terms of decision time.…”

Section: Discussionmentioning

confidence: 99%

Towards Contextual Action Recognition and Target Localization with Active Allocation of Attention

Ognibene

Chinellato

Sarabia

et al. 2012

Biomimetic and Biohybrid Systems

Self Cite

View full text Add to dashboard Cite

Abstract. Exploratory gaze movements are fundamental for gathering the most relevant information regarding the partner during social interactions. We have designed and implemented a system for dynamic attention allocation which is able to actively control gaze movements during a visual action recognition task. During the observation of a partner's reaching movement, the robot is able to contextually estimate the goal position of the partner hand and the location in space of the candidate targets, while moving its gaze around with the purpose of optimizing the gathering of information relevant for the task. Experimental results on a simulated environment show that active gaze control provides a relevant advantage with respect to typical passive observation, both in term of estimation precision and of time required for action recognition.

show abstract

“…In these experiments, the robot associated self-generated actions with the feedback they produce once executed (including learning the feedback delays in the motor system). ( Demiris and Hayes, 2002) have described the relation of this process to a biological counterpart, the mirror system (Gallese et al, 1996), offering a number of explanations and testable predictions Hayes 2002, Demiris andSimmons, 2006), for example, a predicted dependency of the firing rate of the macaque monkey mirror neurons to the velocity profile of the demonstrated act.…”

Section: Principlesmentioning

confidence: 99%

“…Recent evidence on how infants encode goals suggests hierarchical representations Gleissner et al 2000, Wohlschlager, 2003, and recent brain imaging data have also begun to shed light into these hierarchical representations in adults (Hamilton and Grafton, 2007). In robots, hierarchical formulations have been proposed and used Johnson, 2003, Tani andNolfi 1999), but their relation to biological data has not been explored (but see (Byrne andRusson 1998, Demiris andSimmons 2006)). …”

Section: Hierarchical Organisation Of the Inverse And Forward Modelsmentioning

confidence: 99%

Prediction of intent in robotics and multi-agent systems

Demiris

2007

Cogn Process

Self Cite

109

View full text Add to dashboard Cite

Moving beyond the stimulus contained in observable agent behaviour, i.e. understanding the underlying intent of the observed agent is of immense interest in a variety of domains that involve collaborative and competitive scenarios, for example assistive robotics, computer games, robot-human interaction, decision support and intelligent tutoring. This review paper examines approaches for performing action recognition and prediction of intent from a multidisciplinary perspective, in both single robot and multi-agent scenarios, and analyses the underlying challenges, focusing mainly on generative approaches.

show abstract

Perceiving the unusual: Temporal properties of hierarchical motor representations for action perception

Cited by 26 publications

References 38 publications

Efficient template-based path imitation by invariant feature mapping

Efficient template-based path imitation by invariant feature mapping

Towards Contextual Action Recognition and Target Localization with Active Allocation of Attention

Prediction of intent in robotics and multi-agent systems

Contact Info

Product

Resources

About