機器人運動/軌跡規劃問題可定義一個最優控制/隨機最優控制問題。通過線性/非線性規劃求解器來求解軌跡規劃問題。
Some useful links:
1. Deep Reinforcement Learning and Control
"Optimal Control, TrajectoryOptimization, Learning Dynamics"點擊打開鏈接
"Optimal Control, TrajectoryOptimization, and Planning"點擊打開鏈接
2. optimal control
"optimal control" -Benoit Chachuat 點擊打開鏈接
3. Related code
"Optimal Control Using Control Vector Parameterization"點擊打開鏈接
"iLQG/DDP trajectory optimization"點擊打開鏈接
4. Active slam
Optimiaztion metric : Optimal design optimal design
注：以上鍊接均來自網絡轉載