A survey of robot learning from demonstration
Explore this paper's citation graph
Summary
A comprehensive survey of robot Learning from Demonstration (LfD), a technique that develops policies from example state to action mappings, which analyzes and categorizes the multiple ways in which examples are gathered, as well as the various techniques for policy derivation.
- Type
- article
- Published
- 2009-05-01
- Cited by
- 4,067
- References
- 113
- OpenAlex
- https://openalex.org/W1986014385
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:1045325
Keywords
Computer science, Categorization, Teleoperation, Robot, Matching (statistics)
References
- Learning from demonstration and adaptation of biped locomotion
- Reinforcement Learning with Human Teachers: Evidence of Feedback and Guidance with Implications for Learning Performance
- The Elements of Statistical Learning: Data Mining, Inference, and Prediction
- Interactive task training of a mobile robot through human gesture recognition
- Robot Programming by Demonstration
- Locally Weighted Projection Regression: Incremental Real Time Learning in High Dimensional Space
- A multi-agent system for programming robots by human demonstration
- Primitive-Based Movement Classification for Humanoid Imitation
- Imitation in Animals and Artifacts
- Teaching sequential tasks with repetition through demonstration
- On integrating apprentice learning and reinforcement learning
- Correcting and improving imitation models of humans for Robosoccer agents
- Locally Weighted Learning
- Skill acquisition from human demonstration using a hidden Markov model
- Confidence-based policy learning from demonstration using Gaussian mixture models
- Mobile robot programming using natural language
- Learning procedural knowledge through observation
- Programming full-body movements for humanoid robots by observation
- Situated robot learning for multi-modal instruction and imitation of grasping
- Using perspective taking to learn from ambiguous demonstrations
Cited by
- Towards Enabling a Robot to Effectively Assist People in Human-Occupied Environments
- How Humans Teach Agents - A New Experimental Perspective
- Human-robot skills transfer interfaces for a flexible surgical robot
- Apprendre à un robot à reconnaître des objets visuels nouveaux et à les associer à des mots nouveaux : le rôle de l'interface
- Wheeled-Robot Navigation with Velocity Updating on Rough Terrains
- A Learning-Based Hierarchical Control Scheme for an Exoskeleton Robot in Human–Robot Cooperative Manipulation
- Formalizing Human-Robot Mutual Adaptation: A Bounded Memory Model
- Toward an Interactive Reinforcement Based Learning Framework for Human Robot Collaborative Assembly Processes
- Learning to Play Games from Multiple Imperfect Teachers
- Whom Will an Intrinsically Motivated Robot Learner Choose to Imitate from
- Multi Robot Learning by Demonstration
- Autonomous Skill Acquisition on a Mobile Manipulator
- Modeling Purposeful Adaptive Behavior with the Principle of Maximum Causal Entropy
- Contribution à la modélisation et la commande robuste de robots manipulateurs à articulations flexibles. Applications à la robotique interactive.
- Acquisition of Qualitative Spatial Representation by Visual Observation
- Local model predictive control for navigation of a wheeled mobile robot using monocular information
- Towards Imitation Learning of Dynamic Manipulation Tasks: A Framework to Learn from Failures
- Cognition Rehearsed: Recognition and Reproduction of Demonstrated Behavior; Robotövningar: Igenkänning och återgivande av demonstrerat beteende
- Studies on Interactive Knowledge Acquisition and Reuse for Teaching Industrial Robots
- Is Someone in this Office Available to Help Me?
Related papers
- Teleoperation of mobile robots
- Teleoperation Transparency Using Model Predictive Control
- Competitive Multi-robot Teleoperation
- A Survey of high-level teleoperation, monitoring and task assignment to Autonomous Mobile Robots
- TELEOPERATION THROUGH LARGE TIME DELAYAPPLYING TELEPROGRAMMING
- Stabilization of Teleoperation Systems with Communication Delays: An IMC Approach
- 1kHz is not enough — How to achieve higher update rates with a bilateral teleoperation system based on commercial hardware
- Quantitative Absolute Transparency for Bilateral Teleoperation of Mobile Robots
- Analysis and Design for Networked Teleoperation System
- Overview and Prospect of Key Technologies of Teleoperation of Space Robot