Reasoning

This virtual research lab explores reactive motion generation through reasoning. We propose image schema-based reasoning for decision-making within motion controllers. Our reasoner is tightly coupled with the controller, continuously monitoring actions and inferring motion primitives to adapt to dynamic environments. The symbolic theory and the reasoner evaluating it can be exchanged in a plug and play way. By providing real-time feedback, the reasoner enables the controller to make informed decisions and generate appropriate motion responses.

The Body Motion Problem (BMP) is a fundamental challenge in robotics, addressing how robots can compute goal-directed, context-sensitive motions to achieve desired outcomes while adapting to real-world constraints. Beyond simple motion generation, BMP requires robots to interpret task goals, infer causal relationships, predict consequences, and dynamically adjust their actions. This makes BMP computationally complex, necessitating a structured approach to problem-solving. To make it tractable, BMP is decomposed into three interdependent subproblems: (1) Identifying Physical Changes required to fulfill a task request, (2) Determining Actions and Forces needed to achieve these changes, and (3) Generating Forces Through Body Motions that execute the necessary movements reliably. By structuring BMP in this way, researchers can systematically analyze and develop solutions that generalize across diverse tasks and environments.