首页|Investigators from University of Michigan Release New Data on Robotics (Learning a Generalizable Trajectory Sampling Distribution for Model Predictive Control)
Investigators from University of Michigan Release New Data on Robotics (Learning a Generalizable Trajectory Sampling Distribution for Model Predictive Control)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Researchers detail new data in Robotic s. According to news reporting originating from Ann Arbor, Michigan, by NewsRx c orrespondents, research stated, “We propose a sample-based model predictive cont rol (MPC) method for collision-free navigation that uses a normalizing flow as a sampling distribution, conditioned on the start, goal, environment, and cost pa rameters. This representation allows us to learn a distribution that accounts fo r both the dynamics of the robot and complex obstacle geometries.” Financial support for this research came from National Science Foundation (NSF).
Ann ArborMichiganUnited StatesNort h and Central AmericaEmerging TechnologiesMachine LearningRobotRoboticsUniversity of Michigan
NETL
NSTL
