Trajectory learning from human demonstrations via manifold mapping

Hiratsuka, Michihisa; Makondo, Ndivhuwo; Rosman, Benjamin; Hasegawa, Osamu

doi:10.1109/iros.2016.7759579

Cited by 5 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An interesting finding that requires further investigation is that, although complex non-linear mappings are generally preferred in most transfer learning problems for robotics, such as shared Autoencoders, Shared-GPLVM [16] and LPA [22,29], simple linear mappings such as Procrustes Analysis could be more beneficial in a case where human demonstrations are used to provide initialization for learning with reinforcement learning for humanoids [51,52], or a case where a human is allowed to provide feedback to the robot learner for correcting its reproductions [48][49][50]. This is because they can learn mappings from very few samples, which is desired for physical robots, and that they preserve the overall gist of the transferred skills, which would guide a reinforcement learner towards relevant spaces for exploration.…”

Section: Discussionmentioning

confidence: 99%

“…Furthermore, goal-directed motions were not addressed in this work. Finally, in our previous work [22] we proposed learning a mapping directly from sensor data (projected onto a human skeletal model) to robot actuator space, using Local Procrustes Analysis (LPA). However, we required that the human teacher and the robot share the same workspace, and we only considered the case of teaching a single robot.…”

Section: Related Workmentioning

confidence: 99%

“…In this paper we propose a data-driven approach based on manifold alignment that is suitable in such cases where knowledge of the kinematic model of the robot learner is not available. This paper is an extension of our previous published work [22], in which we showcased the extraction of simple human movements using a Kinect sensor and transferring them to a single robot, where the workspaces of the human teacher and the robot were assumed to intersect. Here, we formalize the problem and greatly extend our analysis to two humanoids learning more complex tasks from demonstration, showcasing the robustness of our method to differences in kinematics, and a comparison of two manifold alignment techniques.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Non-Linear Manifold Alignment Approach to Robot Learning from Demonstrations

Makondo¹,

Hiratsuka²,

Rosman³

et al. 2018

JRM

Self Cite

View full text Add to dashboard Cite

The number and variety of robots active in real-world environments are growing, as well as the skills they are expected to acquire, and to this end we present an approach for non-robotics-expert users to be able to easily teach a skill to a robot with potentially different, but unknown, kinematics from humans. This paper proposes a method that enables robots with unknown kinematics to learn skills from demonstrations. Our proposed method requires a motion trajectory obtained from human demonstrations via a vision-based system, which is then projected onto a corresponding human skeletal model. The kinematics mapping between the robot and the human model is learned by employing Local Procrustes Analysis, a manifold alignment technique which enables the transfer of the demonstrated trajectory from the human model to the robot. Finally, the transferred trajectory is encoded onto a parameterized motion skill, using Dynamic Movement Primitives, allowing it to be generalized to different situations. Experiments in simulation on the PR2 and Meka robots show that our method is able to correctly imitate various skills demonstrated by a human, and an analysis of the transfer of the acquired skills between the two robots is provided.

show abstract