Motion Planning for Humanoid Robots

Abstract

Humanoid robotics hardware and control techniques have advanced rapidly during the last five years. Presently, several companies have announced the commercial availability of various humanoid robot prototypes. In order to improve the autonomy and overall functionality of these robots, reliable sensors, safety mechanisms, and general integrated software tools and techniques are needed. We believe that the development of practical motion planning algorithms and obstacle avoidance software for humanoid robots represents an important enabling technology. This paper gives an overview of some of our recent efforts to develop motion planning methods for humanoid robots for application tasks involving navigation, object grasping and manipulation, footstep placement, and dynamically-stable full-body motions. We show experimental results obtained by implementations running within a simulation environment as well as on actual humanoid robot hardware.

Multi-Step Motion Planning for Free-Climbing Robots

“…For more general systems (including the climbing robots considered in this paper), it seems impractical to compute the structure of the multi-step motion space exactly. Heuristic search techniques have been used in cases where a predefined set of one-step moves is available [5,21]. If no such set has been predefined, continuous exploration is needed [26,30].…”

“…Therefore, we use an approximate method: for each adjacent stance σ , first we sample transition points q t ∈ F σ ∩ F σ , then we try to construct a continuous path from q s to each q t , using an augmented PRM planner [9]. Similar techniques are used in other multi-step planning algorithms (e.g., [21,26,30]). …”

Fall Prediction for New Sequences of Motions

“…However, the drawback of this method is that "some feasible dynamic motions are inherently impossible to compute with this approach." [4] Though there are planners that will compute dynamically stable motion trajectories offline [5], [6], these planners require an accurate robot model and change the desired motion in terms of the timings and the trajectory. Changing the timings of the desired motion causes the motion to be no longer synchronized to the task and changing the motion trajectory changes the meaning expressed.…”

Development of Path-Finding System for Humanoid Robots Based on Image Pattern Recognition

“…휴머노이드 로봇과 관련된 기존의 연구로는, 로봇 의 안정적인 보행과 관한 연구와 [5][6] , 휴머노이드 로 봇에 장착된 카메라를 통해 수집된 영상 정보를 기 반으로 하는 로봇의 동작을 제어하는 연구가 진행된 바 있다 [7] . 경로인식을 통해 시각장애인을 지원하는 최근의 연구로는 RFID [8] , 초음파 센서 [9] 를 이용한 연구가 진행되었다.…”