Learning from Corrective Demonstrations

Gutierrez, Reymundo A.; Short, Elaine Schaertl; Niekum, Scott; Thomaz, Andrea L.

doi:10.1109/hri.2019.8673287

Cited by 4 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chernova & Thomaz (4) covered techniques for managing the interaction, such as active learning (39,(45)(46)(47)(48) and corrective demonstrations (49,50), in greater detail. Amershi et al (51) presented several case studies that illustrate the importance of studying the users of intelligent systems in order to improve both user experience and robot performance.…”

Section: Active and Interactive Demonstrationsmentioning

confidence: 99%

Recent Advances in Robot Learning from Demonstration

Ravichandar

Polydoros

Chernova

et al. 2020

Annu. Rev. Control Robot. Auton. Syst.

399

198

View full text Add to dashboard Cite

In the context of robotics and automation, learning from demonstration (LfD) is the paradigm in which robots acquire new skills by learning to imitate an expert. The choice of LfD over other robot learning methods is compelling when ideal behavior can be neither easily scripted (as is done in traditional robot programming) nor easily defined as an optimization problem, but can be demonstrated. While there have been multiple surveys of this field in the past, there is a need for a new one given the considerable growth in the number of publications in recent years. This review aims to provide an overview of the collection of machine-learning methods used to enable a robot to learn from and imitate a teacher. We focus on recent advancements in the field and present an updated taxonomy and characterization of existing methods. We also discuss mature and emerging application areas for LfD and highlight the significant challenges that remain to be overcome both in theory and in practice.

show abstract

Section: Active and Interactive Demonstrationsmentioning

confidence: 99%

Recent Advances in Robot Learning from Demonstration

Ravichandar

Polydoros

Chernova

et al. 2020

Annu. Rev. Control Robot. Auton. Syst.

399

198

View full text Add to dashboard Cite

show abstract

“…Gutierrez et al (2018) present an incremental task modification algorithm based on a demonstration that creates and probabilistically selects corrections for structural modifications in a finite-state machine task model. Gutierrez et al (2019) build on this approach by providing a demonstration at or near execution failure so as to only having to locally update the model. The local update procedure determines if the demonstration represents a known primitive (as opposed to a new one), in which case the demonstration is added and the primitive retrained.…”

Section: Related Workmentioning

confidence: 99%

Enabling Fast Instruction-Based Modification of Learned Robot Skills

Frasca

Oosterveld²,

Chita-Tegmark

et al. 2021

AAAI

View full text Add to dashboard Cite

Much research effort in HRI has focused on how to enable robots to learn new skills from observations, demonstrations, and instructions. Less work, however, has focused on how skills can be corrected if they were learned incorrectly, adapted to changing circumstances, or generalized/specialized to different contexts. In this paper, a skill modification framework is introduced that allows users to modify a robot’s stored skills quickly through instructions to (1) reduce inefficiencies, (2) fix errors, and (3) enable generalizations, all in a way for modified skills to be immediately available for task performance. A thorough evaluation of the implemented framework shows the operation of the algorithms integrated in a cognitive robotic architecture on different fully autonomous robots in various HRI case studies. An additional online HRI user study verifies that subjects prefer to quickly modify robot knowledge in the way we proposed in the framework.

show abstract

“…LfD by simply focused on learning a consistent performing policy from a few demonstrations of a simple task with a well-defined starting and goal configuration which often fails for achieving the complex tasks with a single policy. Therefore, learning to represent the complex tasks from unstructured demonstrations provided by sequential sub-tasks, or movement primitives that are associated with generalization, fault detection, fault diagnoses, and task exploration, which may be reusable in complex and multi-step tasks [15], [16]. For this reason, recent work has aimed at associating the multimodal signals and historical experiences the process of learning from demonstrations [17].…”

Section: Introductionmentioning

confidence: 99%

Incremental Learning Introspective Movement Primitives From Multimodal Unstructured Demonstrations

Yan

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Learning movement primitive from unstructured demonstrations has become a popular topic in recent years, which provides a natural way to endow human-inspired skills to robots. The main idea of movement primitives is that should suffice to reconstruct a large set of complex manipulation tasks. However, conventional learning methods mostly focus on the kinesthetic variables and ignore those critical introspective capacities in manipulation such as movement generalization and assessment of the sensory signals. In this paper, we investigate the association of generalization, fault detection, fault diagnoses, and task exploration during manipulation task, and call such movement primitives augmented with introspective capacities Introspective Movement Primitives (IMP). With our previous work, this paper mainly addresses how IMPs can be acquired by assessing the quality of multimodal sensory data of unstructured demonstrations and how they can incrementally create manipulation task by reverse execution and human interaction. Experimental evaluation on a human-robot collaborative packaging task with a Rethink Baxter robot, results indicate that our proposed method can effectively increase robustness towards external perturbations and adaptive exploration during robot manipulation task.

show abstract

Learning from Corrective Demonstrations

Cited by 4 publications

References 10 publications

Recent Advances in Robot Learning from Demonstration

Recent Advances in Robot Learning from Demonstration

Enabling Fast Instruction-Based Modification of Learned Robot Skills

Incremental Learning Introspective Movement Primitives From Multimodal Unstructured Demonstrations

Contact Info

Product

Resources

About