SACBP: Belief space planning for continuous-time dynamical systems via stochastic sequential action control.
Haruki NishimuraMac SchwagerPublished in: Int. J. Robotics Res. (2021)
Keyphrases
- dynamical systems
- belief space
- planning under uncertainty
- partially observable
- partially observable markov decision processes
- state space
- control theory
- initial state
- action sequences
- dynamic systems
- belief state
- action space
- reinforcement learning
- predictive state representations
- continuous state
- planning problems
- heuristic search
- nonlinear dynamical systems
- action selection
- optimal control
- control system
- motion planning
- dynamic programming
- optimal policy
- dynamic environments
- markov chain
- learning algorithm
- stochastic processes
- human body
- markov decision problems
- monte carlo
- human actions