-Translate the map of your environment (with obstacles) into C-space, and create a visualization of this map with initial and goal states indicated
-Given a set of points V in C-space and a single other target point, write and test a function to determine which of the points in V is closest to the target
-Given arbitrary initial and target robot states (in C-space), write and test a function to generate a smooth achievable trajectory from the initial state towards the target lasting 1 second. What are the control inputs for this trajectory?
-Given your C-space map and an arbitrary robot trajectory, write and test a function to determine whether this trajectory is collision free
- Put these functions together to implement an RRT planner on your map to generate a trajectory from a
specified initial state to the desired goal state. Visualize the evolution of the RRT as well as the resulting trajectory
-Since your system dynamics are reversible, modify your planner to generate robust trajectories to the goal state from arbitrary initial states.
-Optionally, improve on this planner using RRT* or LQR trees
-Run some examples that demonstrate the performance (in terms of computational efficiency, trajectory efficiency, and obstacle avoidance) of your planner as your robot tries to achieve various goals (such as head-in parking and parallel parking between other such parked vehicles). Clearly describe the experiments that were run, the data that was gathered, and the process by which you use that data to characterize the performance of your planner.
- How much relative computational cost is associated with the various operations of the RRT planner?
- . If the obstacles were dynamic, and themselves moved, you would need to re-plan trajectories to account for
the varying environment. Based on the computational time of your planner, what obstacle dynamics would
you be able to handle in real time?
-Qualitatively describe some conclusions about the effectiveness of your planner for potential tasks your robot
may encounter. How might you improve it?
About the recuiterMember since Mar 14, 2020 Nikul
from Queensland, Australia