Model-based learning from demonstration with the uBot-5

Abstract: We propose an approach to control learning from demonstration that first segments demonstration trajectories to identify subgoals, then uses model-based control methods to sequentially reach these subgoals to solve the overall task. Using this approach, we show that a mobile robot is able to solve a combined navigation and manipulation task robustly after observing only a single successful trajectory.

For more details, please see:

S.R. Kuindersma, G.D. Konidaris, R.A. Grupen, A.G. Barto. Learning from a Single Demonstration: Motion Planning with Skill Segmentation (extended abstract). NIPS Workshop on Learning and Planning from Batch Time Series Data. December 2010.

G.D. Konidaris, S.R. Kuindersma, A.G. Barto, R.A. Grupen. Constructing Skill Trees for Reinforcement Learning Agents from Demonstration Trajectories. In Advances in Neural Information Processing Systems 23 (NIPS). December 2010.

Category:

Science & Technology

Tags:

• robotics
• learning from demonstration
• AI
• robot learning