ROBOT6200

Formulate robot motion planning problems as constrained nonlinear optimizationproblems and solve them using optimization methods.

Formulate robot motion planning problems as graph search problems and solvethese problems with graph search methods including Depth First Search (DFS),Breadth First Search (BFS), Uniform Cost Search (UCS) and A*.

Formulate robot motion planning problems as Markov Decision Processes (MDPs) andsolve them using value iteration and policy iteration.

Frame a novel robotics application as a motion planning problem and select anappropriate algorithm class to solve the problem.

Solve robot motion planning problems for both lower dimensional robots and realrobot arms in simulation using sampling-based methods including Rapidly-exploringRandom Trees (RRT) and Probabilistic Roadmaps (PRM).

Formulate robot motion planning problems as constrained nonlinear optimization problems and solve them using optimization methods.

Formulate robot motion planning problems as graph search problems and solve these problems with graph search methods including Depth First Search (DFS), Breadth First Search (BFS), Uniform Cost Search (UCS) and A*

Formulate robot motion planning problems as Markov Decision Processes (MDPs) and solve them using value iteration and policy iteration.

Frame a novel robotics application as a motion planning problem and select an appropriate algorithm class to solve the problem.

Solve robot motion planning problems for both lower dimensional robots and real robot arms in simulation using sampling-based methods including Rapidly-exploring Random Trees (RRT) and Probabilistic Roadmaps (PRM)

Formulate robot motion planning problems as constrained nonlinear optimization problems and solve them using optimization methods.

Formulate robot motion planning problems as graph search problems and solve these problems with graph search methods including Depth First Search (DFS), Breadth First Search (BFS), Uniform Cost Search (UCS) and A*

Formulate robot motion planning problems as Markov Decision Processes (MDPs) and solve them using value iteration and policy iteration.

Frame a novel robotics application as a motion planning problem and select an appropriate algorithm class to solve the problem.

Solve robot motion planning problems for both lower dimensional robots and real robot arms in simulation using sampling-based methods including Rapidly-exploring Random Trees (RRT) and Probabilistic Roadmaps (PRM).