CAREER: Legged Locomotion Across Scales: Closing the Loop Between Task Planning and Motion Control

点击翻译按钮获取中文摘要

This award seeks to introduce tightly integrated locomotion control and motion planning strategies for agile, highly-mobile legged robots with radically different sizes and morphologies. To realize the potential of these machines in real-world applications, basic movements must be composed to synthesize more complex locomotion behaviors that achieve desirable high-level planning objectives. As dynamic legged robots are becoming increasingly more capable, the need for hierarchically consistent locomotion planning strategies that translate descending task-level commands to suitable low-level control actions that harness the platform's locomotion capabilities becomes pressing. To address this need, this effort pursues new directions (i) in dynamic legged locomotion, by offering a portable library of locomotion primitives; (ii) in robot control, by providing constructive feedback reduction strategies and stochastic data-driven methods that map complex legged robot platforms to behavior-encoding target models; and (iii) in hybrid systems, by introducing a framework for complexity reduction through multiple layers of information processing and control action. This research effort seeks to enable legged machines to perform real-world tasks reliably and efficiently. This way, it promotes many different applications, including industrial, agricultural, and emergency response applications that require highly mobile and versatile robots. This effort also includes substantial educational and community outreach components, aiming at attracting underrepresented groups to science, technology, engineering, and mathematics. In addition, by pairing high-school teachers with graduate students, this effort addresses the critical need for K-12 teachers to stay current and articulate their teaching with the demands of college courses.