… into the policy while giving up on clearly unpromising paths [59]. We propose to jointly train
the guidance policy with the local motion planner allowing the trained policy to directly im…

… existing motion planning algorithms while adding perspectives and practical examples from
UAV guidance … of this MA based guidance policy for online rotorcraft guidance. In this form of …

… may change over time, requiring real-time motion planning and guidance algorithms. … , we
compared the nominal and robust policy using closed-loop guidance, in which the guidance …

… We propose a motion planning method for dual-arm free-floating space robots based on
reinforcement learning. The problem of slow and unstable convergence of reinforcement …

… learn a control policy that will enable a robot to autonomously execute the task … environment
using the derived cost metric for guidance. An overview of the approach is shown in Fig. 2. …

This paper addresses the problem of motion planning (MP) in dynamic environments. It is first
argued that dynamic environments impose a real-time constraint upon MP: it has a limited …

… of the system in the environment and generating a policy over the approximated Markov
states. Examples of such motion planners include stochastic motion roadmap (SMR) [9] and …

… This paper presents a motion planning, guidance, and control … The motion planning algorithm
is based on the angle-guidance fast-marching square method (AFMS), and the guidance …

… More specifically, this paper considers the problem of probabilistically safe motion planning
to avoid one or more dynamic obstacles with uncertain motion patterns. While existing …

… Stability and robustness is very important to a motion plan, and show how reliable the motion
plan is in response to system perturbations. Some perturbations are caused by numerical er…