Planning Collision‐Free Reaching Motions for Interactive Object Manipulation and Grasping

Abstract

We present new techniques that use motion planning algorithms based on probabilistic roadmaps to control 22 degrees of freedom (DOFs) of human‐like characters in interactive applications. Our main purpose is the automatic synthesis of collision‐free reaching motions for both arms, with automatic column control and leg flexion. Generated motions are collision‐free, in equilibrium, and respect articulation range limits. In order to deal with the high (22) dimension of our configuration space, we bias the random distribution of configurations to favor postures most useful for reaching and grasping. In addition, extensions are presented in order to interactively generate object manipulation sequences: a probabilistic inverse kinematics solver for proposing goal postures matching pre‐designed grasps; dynamic update of roadmaps when obstacles change position; online planning of object location transfer; and an automatic stepping control to enlarge the character's reachable space. This is, to our knowledge, the first time probabilistic planning techniques are used to automatically generate collision‐free reaching motions involving the entire body of a human‐like character at interactive frame rates. Categories and Subject Descriptors (according to ACM CCS): I.3.7 [Computer Graphics]: Three‐Dimensional Graphics and Realism

Collision-Free Humanoid Reaching: Past, Present and Future

“…More recent work by Kagami et al (2003) uses stereo vision to construct a geometric model of a static environment and motion planning and inverse kinematics to reach to and grasp a bottle with a stationary humanoid robot. Liu & Badler (2003); Kallmann et al (2003); Bertram et al (2006) and focused on developing algorithms for humanoid reaching; the algorithms in the latter two works are probabilistically complete, while the algorithms in (Liu & Badler, 2003) and (Kallmann et al, 2003) are not complete in any sense. All four works assumed static environments, perfect control and holonomic constraints.…”

“…The RRT has been applied successfully to reaching for humanoids in virtual environments in (Kuffner, Jr., 1998); (Liu & Badler, 2003); (Kallmann et al, 2003); (Bertram et al, 2006) and , among others. Additionally, the RRT has been applied to reaching for an embodied humanoid by Kagami et al (2003), although, as stated in Section 2, the environment was considered to be stationary and locomotion was not utilized.…”

Environment-Aware Postural Control of Virtual Humans for Real-time Applications

“…al have applied them to a humanoid robot with 33 DOFs, but only for offline applications [15]. A similar approach by Kallmann et al is able to generate reach and grasp motions in real-time for a 22 DOF humanoid [16], but the range of available motions is restricted to those precomputed in a roadmap [17]. In general, all path planning techniques have the weakness that the user is required to specify a final collision-free posture.…”

Combinatorial Motion Planning

“…RRTs have been used in several applications, and many variants have been developed [18,24,26,37,38,42,47,57,65,85,88,87,92,113,120,121,156,157,162,168,169]. Originally, they were developed for planning under differential constraints, but most of their applications to date have been for ordinary motion planning.…”