Synthesis and Stabilization of Complex Behaviors Through Online Trajectory Optimization

Yuval Tassa,Tom Erez,Emanuel Todorov

Proceedings of the ... IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE/RSJ...（2012）

Univ Washington

被引用1218|浏览187

摘要

We present an online trajectory optimization method and software platform applicable to complex humanoid robots performing challenging tasks such as getting up from an arbitrary pose on the ground and recovering from large disturbances using dexterous acrobatic maneuvers. The resulting behaviors, illustrated in the attached video, are computed only 7 × slower than real time, on a standard PC. The video also shows results on the acrobot problem, planar swimming and one-legged hopping. These simpler problems can already be solved in real time, without pre-computing anything.

更多

查看译文

关键词

control system synthesis,humanoid robots,legged locomotion,optimisation,predictive control,stability,trajectory control,MPC,acrobot problem,arbitrary pose,complex behavior stabilization,complex behavior synthesis,complex humanoid robot,dexterous acrobatic maneuver,disturbance recovery,model predictive control,one-legged hopping,online trajectory optimization,planar swimming,software platform