Motion Planning on Visual Manifolds
This work addresses motion planning for robots and digital avatars without prior geometric information, offering a novel approach but is incremental in its application of manifold learning.
The authors tackled the problem of robot motion planning without geometric knowledge by introducing Visual Configuration Space (VCS), enabling agents to discover body structure and plan obstacle-free motions using images, with applications in geometry-free models, explaining infant learning, and generating avatar animations.
In this thesis, we propose an alternative characterization of the notion of Configuration Space, which we call Visual Configuration Space (VCS). This new characterization allows an embodied agent (e.g., a robot) to discover its own body structure and plan obstacle-free motions in its peripersonal space using a set of its own images in random poses. Here, we do not assume any knowledge of geometry of the agent, obstacles or the environment. We demonstrate the usefulness of VCS in (a) building and working with geometry-free models for robot motion planning, (b) explaining how a human baby might learn to reach objects in its peripersonal space through motor babbling, and (c) automatically generating natural looking head motion animations for digital avatars in virtual environments. This work is based on the formalism of manifolds and manifold learning using the agent's images and hence we call it Motion Planning on Visual Manifolds.