The Modular Behavioral Environment for Humanoids and other Robots (MoBeE)

To produce even the simplest human-like behaviors, a humanoid robot must be able to see, act, and react,\udwithin a tightly integrated behavioral control system. Although there exists a rich body of literature in Computer\udVision, Path Planning, and Feedback Control, wherein many critical subproblems are addressed individually,\udmost demonstrable behaviors for humanoid robots do not effectively integrate elements from all three\uddisciplines. Consequently, tasks that seem trivial to us humans, such as pick-and-place in an unstructured environment,\udremain far beyond the state-of-the-art in experimental robotics. We view this primarily as a software\udengineering problem, and have therefore developed MoBeE, a novel behavioral framework for humanoids and\udother complex robots, which integrates elements from vision, planning, and control, facilitating the synthesis\udof autonomous, adaptive behaviors. We communicate the efficacy of MoBeE through several demonstrative\udexperiments. We first develop Adaptive Roadmap Planning by integrating a reactive feedback controller into\uda roadmap planner. Then, an industrial manipulator teaches a humanoid to localize objects as the two robots\udoperate autonomously in a shared workspace. Finally, an integrated vision, planning, control system is applied\udto a real-world reaching task using the humanoid robot