Library-based methods are known to be very effective for fast motion planning by adapting an experience retrieved from a precomputed library. This article presents CoverLib, a principled approach for constructing and utilizing such a library. CoverLib iteratively adds an experience-classifier-pair to the library, where each classifier corresponds to an adaptable region of the experience within the problem space. This iterative process is an active procedure, as it selects the next experience based on its ability to effectively cover the uncovered region. During the query phase, these classifiers are utilized to select an experience that is expected to be adaptable for a given problem. Experimental results demonstrate that CoverLib effectively mitigates the trade-off between plannability and speed observed in global (e.g. sampling-based) and local (e.g. optimization-based) methods. As a result, it achieves both fast planning and high success rates over the problem domain. Moreover, due to its adaptation-algorithm-agnostic nature, CoverLib seamlessly integrates with various adaptation methods, including nonlinear programming-based and sampling-based algorithms.
16 April 2021 in IEEE Robotics and Automation Letters
We propose an algorithm that enables active learning of a manipulation skill that is robust to the estimation error of the world. We first propose a concept of the feasible error region (FER) that is unique to each manipulation parameter. As the name implies, FER is a region of estimation errors even with which the manipulation still succeeds. We introduce the volume of the FER as a robustness measure of a manipulation parameter. Finding a parameter that maximizes such volume allows us to obtain the most robust manipulation skill according to our criteria. This maximization is not tractable with naive optimization methods. Thus, we introduce two natural assumptions regarding the FER and by taking advantage of these assumptions, we develop an active learning algorithm capable of achieving the volume maximization. As well as numerical experiments using toy models, we apply the algorithm to a robotic task in the physics simulator and two tasks in the real world. We demonstrate the validity of our approach, at the same time giving a discussion on limitations.
1 January 2026 in IEEE Robotics and Automation Practice