Efficient template-based path imitation by invariant feature mapping

Wu, Yan; Demiris, Yiannis

doi:10.1109/robio.2009.5420496

Cited by 5 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, not only should the algorithm be able to generate such path with great level of stability, but more importantly have some resemblance to the path produced by human under similar circumstances. This has been demonstrated in our previous works [9], [14].…”

Section: The Hila-osila Frameworksupporting

confidence: 80%

“…We showed in our previous work, by cross-validating the results on a set of 75 experiments conducted on human subjects [14], that the OSILA is capable of reproducing satisfactory path in imitating simple tasks. In the following sections of this paper, we will present the HILA-OSILA framework and extend the same dataset and evaluating metrics to test the statistical fitness for breaking-up the templates in contrast with the original mappings.…”

Section: Introductionmentioning

confidence: 83%

“…In previous work [14], we suggested that this was due to the lack of complete invariant information in the complex cases. Thus, by breaking the paths into smaller segments, we introduced extra spatial constraints into mapping.…”

Section: A Experiments Amentioning

confidence: 95%

“…The benchmarking dataset of 75 trials on 5 different experiments was taken from [14] and illustrated in Fig. 5.…”

Section: A Experiments Amentioning

confidence: 99%

“…The hypothesised paths are denoted by black slashes in the diagrams. Detailed descriptions of the experiments can be found in [14].…”

Section: A Experiments Amentioning

confidence: 99%

See 4 more Smart Citations

Hierarchical learning approach for one-shot action imitation in humanoid robots

Demiris

2010

2010 11th International Conference on Control Automation Robotics &Amp; Vision

Self Cite

View full text Add to dashboard Cite

Abstract-We consider the issue of segmenting an action in the learning phase into a logical set of smaller primitives in order to construct a generative model for imitation learning using a hierarchical approach. Our proposed framework, addressing the "how-to" question in imitation, is based on a oneshot imitation learning algorithm. It incorporates segmentation of a demonstrated template into a series of subactions and takes a hierarchical approach to generate the task action by using a finite state machine in a generative way. Two sets of experiments have been conducted to evaluate the performance of the framework, both statistically and in practice, through playing a tic-tac-toe game. The experiments demonstrate that the proposed framework can effectively improve the performance of the one-shot learning algorithm and reduce the size of primitive space, without compromising the learning quality.

show abstract

Section: The Hila-osila Frameworksupporting

confidence: 80%

Section: Introductionmentioning

confidence: 83%

Section: A Experiments Amentioning

confidence: 95%

“…The benchmarking dataset of 75 trials on 5 different experiments was taken from [14] and illustrated in Fig. 5.…”

Section: A Experiments Amentioning

confidence: 99%

“…The hypothesised paths are denoted by black slashes in the diagrams. Detailed descriptions of the experiments can be found in [14].…”

Section: A Experiments Amentioning

confidence: 99%

See 3 more Smart Citations

Hierarchical learning approach for one-shot action imitation in humanoid robots

Demiris

2010

2010 11th International Conference on Control Automation Robotics &Amp; Vision

Self Cite

View full text Add to dashboard Cite

show abstract

Wavelet based OFTM for learning stirring food by imitation

Falahi

Sobhiyeh

Rezaie

et al. 2015

2015 International Conference on Advanced Robotics (ICAR)

View full text Add to dashboard Cite

Towards One Shot Learning by imitation for humanoid robots

Demiris

2010

2010 IEEE International Conference on Robotics and Automation

Self Cite

View full text Add to dashboard Cite

Abstract-Teaching a robot to learn new knowledge is a repetitive and tedious process. In order to accelerate the process, we propose a novel template-based approach for robot arm movement imitation. This algorithm selects a previously observed path demonstrated by a human 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 a combination of minimum distortion and minimum energy strategies. This One-Shot Learning algorithm is capable of not only mapping simple point-to-point paths but also adapting to more complex tasks such as those involving forced waypoints. As compared to traditional methodologies, our work require neither extensive training for generalisation nor expensive run-time computation for accuracy. This algorithm has been statistically validated using cross-validation of grasping experiments as well as tested for practical implementation on the iCub humanoid robot for playing the tic-tac-toe game.

show abstract

Efficient template-based path imitation by invariant feature mapping

Cited by 5 publications

References 22 publications

Hierarchical learning approach for one-shot action imitation in humanoid robots

Hierarchical learning approach for one-shot action imitation in humanoid robots

Wavelet based OFTM for learning stirring food by imitation

Towards One Shot Learning by imitation for humanoid robots

Contact Info

Product

Resources

About