Towards One Shot Learning by imitation for humanoid robots

Wu, Yan; Demiris, Yiannis

doi:10.1109/robot.2010.5509429

Cited by 21 publications

(2 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For efficiency, and since human supervision may be limited in real-world conditions, in this study, only a small number of such tutoring examples are created for each new task in which the robot shows reduced task performance. This approach is analogous to few-shot learning, which has also been applied in teaching robots by imitation [55]. These new tutoring examples are combined with rehearsal data to build a dataset for incremental learning.…”

Section: Incremental Learningmentioning

confidence: 99%

Incremental Learning of Goal-Directed Actions in a Dynamic Environment by a Robot Using Active Inference

Matsumoto,

Ohata,

Tani

2023

Entropy

View full text Add to dashboard Cite

This study investigated how a physical robot can adapt goal-directed actions in dynamically changing environments, in real-time, using an active inference-based approach with incremental learning from human tutoring examples. Using our active inference-based model, while good generalization can be achieved with appropriate parameters, when faced with sudden, large changes in the environment, a human may have to intervene to correct actions of the robot in order to reach the goal, as a caregiver might guide the hands of a child performing an unfamiliar task. In order for the robot to learn from the human tutor, we propose a new scheme to accomplish incremental learning from these proprioceptive–exteroceptive experiences combined with mental rehearsal of past experiences. Our experimental results demonstrate that using only a few tutoring examples, the robot using our model was able to significantly improve its performance on new tasks without catastrophic forgetting of previously learned tasks.

show abstract

Section: Incremental Learningmentioning

confidence: 99%

Incremental Learning of Goal-Directed Actions in a Dynamic Environment by a Robot Using Active Inference

Matsumoto,

Ohata,

Tani

2023

Entropy

View full text Add to dashboard Cite

show abstract

“…In contrast, learning by human demonstration directly incorporates human expertise but typically requires extensive human involvement. Demonstrations are often provided kinesthetically [18], in simulation [19], or via motion capture [20]. Processing techniques often involve keyframes [21], segmentation [22], [23], constraint extraction [24], [25], and reproduction [26], [27].…”

Section: Related Workmentioning

confidence: 99%

Helping Robots Learn: A Human-Robot Master-Apprentice Model Using Demonstrations via Virtual Reality Teleoperation

DelPreto¹,

Lipton²,

Sanneman³

et al. 2020

2020 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

As artificial intelligence becomes an increasingly prevalent method of enhancing robotic capabilities, it is important to consider effective ways to train these learning pipelines and to leverage human expertise. Working towards these goals, a master-apprentice model is presented and is evaluated during a grasping task for effectiveness and human perception. The apprenticeship model augments self-supervised learning with learning by demonstration, efficiently using the human's time and expertise while facilitating future scalability to supervision of multiple robots; the human provides demonstrations via virtual reality when the robot cannot complete the task autonomously. Experimental results indicate that the robot learns a grasping task with the apprenticeship model faster than with a solely self-supervised approach and with fewer human interventions than a solely demonstration-based approach; 100% grasping success is obtained after 150 grasps with 19 demonstrations. Preliminary user studies evaluating workload, usability, and effectiveness of the system yield promising results for system scalability and deployability. They also suggest a tendency for users to overestimate the robot's skill and to generalize its capabilities, especially as learning improves.

show abstract

Playback Robot Programming with Loop Increments

Riedl¹,

Henrich²

2022

Annals of Scientific Society for Assembly, Handling and Industrial Robotics 2021

View full text Add to dashboard Cite

Playback robot programming is fast and easy to use for non-experts, because the robot only needs to be manually guided. However, it is only capable of replaying the trajectory exactly as it was taught. We present the concept of loop increments for playback programmed robots to allow the user to teach tasks like palletizing or stacking without having to explicitly guide the robot through each trajectory. Only the base trajectory for one repetition needs to be program med. After each loop iteration, the user-defined increment is added to the incremental configurations, e.g. to the pick or place configurations. To achieve this, two methods of defining the loop increments are shown. Afterwards, linear, Gaussian, and cosine blending functions in combination with the point and interval method are introduced for weighting the increments and as a foundation for the adaption algorithm. The evaluation showed, that the cosine blending function with the interval method best fits the needs of our programming system.

show abstract

Towards One Shot Learning by imitation for humanoid robots

Cited by 21 publications

References 24 publications

Incremental Learning of Goal-Directed Actions in a Dynamic Environment by a Robot Using Active Inference

Incremental Learning of Goal-Directed Actions in a Dynamic Environment by a Robot Using Active Inference

Helping Robots Learn: A Human-Robot Master-Apprentice Model Using Demonstrations via Virtual Reality Teleoperation

Playback Robot Programming with Loop Increments

Contact Info

Product

Resources

About