Built and tested the robotic arm<\/p>\n
Worked on RRT octree implementation<\/p>\n
This week I finished the RRT implementation on the octree.\u00a0 Upon finishing this implementation and further discussions with my teammates, we decided that a dense matrix implementation would be ideal for the FPGA.\u00a0 For this reason I developed functions to compress the octree into a dense matrix.\u00a0 I then implemented RRT on the dense matrix.\u00a0 These backend implementations are abstracted away in the perception simulator.\u00a0 Swapping out the octree and dense matrix backends is as simple as toggling the “COMPRESSED” macro in the header file.<\/p>\n
While the current RRT implementations are operational, they are not optimized.\u00a0 My current focus has been on getting a baseline implementation working.\u00a0 I have added some notes to our code base and have developed some ideas on future optimizations.\u00a0 I believe that the largest speedup will be found in optimizing search for the nearest neighbor to a specific voxel.\u00a0 This computation is highly parallelizable and there are some heuristics about the order in which the state space is traversed that should be followed.<\/p>\n
I have begun implementing A* for the dense matrix backend and\u00a0 I am targeting completing it by the end of the weekend.\u00a0 When I finish A*, the baseline implementation of our motion planning module will be complete.\u00a0 From here I will transition to work on inverse-kinematics and arm control modules.<\/p>\n
Finish implementing A* on dense matrix<\/p>\n
Continue work on inverse kinematics and arm control<\/p>\n","protected":false},"excerpt":{"rendered":"
What I did last week Built and tested the robotic arm Worked on RRT octree implementation What I did this week This week I finished the RRT implementation on the octree.\u00a0 Upon finishing this implementation and further discussions with my teammates, we decided that a dense matrix implementation would be ideal for the FPGA.\u00a0 For … <\/p>\n