Learning Trajectory Preferences for Manipulators via Iterative Improvement

Abstract

We consider the problem of learning good trajectories for manipulation tasks. This is challenging because the criterion defining a good trajectory varies with users, tasks and environments. In this paper, we propose a co-active online learning framework for teaching robots the preferences of its users for object manipulation tasks. The key novelty of our approach lies in the type of feedback expected from the user: the human user does not need to demonstrate optimal trajectories as training data, but merely needs to iteratively provide trajectories that slightly improve over the trajectory currently proposed by the system. We argue that this co-active preference feedback can be more easily elicited from the user than demonstrations of optimal trajectories, which are often challenging and non-intuitive to provide on high degrees of freedom manipulators. Nevertheless, theoretical regret bounds of our algorithm match the asymptotic rates of optimal trajectory algorithms. We demonstrate the generalizability of our algorithm on a variety of grocery checkout tasks, for whom, the preferences were not only influenced by the object being manipulated but also by the surrounding environment.\footnote{For more details and a demonstration video, visit: \url{http://pr.cs.cornell.edu/coactive}}

9 pages. To appear in NIPS 2013

References in corpus (3)

• Continuous Inverse Optimal Control with Locally Optimal Examples
• Learning Object Arrangements in 3D Scenes using Human Context
• Online Structured Prediction via Coactive Learning

Cited by in corpus (5)

• RoboBrain: Large-Scale Knowledge Engine for Robots
• Smooth Imitation Learning for Online Sequence Prediction
• Preference-based Reinforcement Learning with Finite-Time Guarantees
• Dueling RL: Reinforcement Learning with Trajectory Preferences
• From Demonstrations to Task-Space Specifications: Using Causal Analysis to Extract Rule Parameterization from Demonstrations