search

ai-winter / ros_motion_planning

Motion planning and Navigation of AGV/AMR：ROS planner plugin implementation of A*, JPS, D*, LPA*, D* Lite, Theta*, RRT, RRT*, RRT-Connect, Informed RRT*, ACO, PSO, Voronoi, PID, LQR, MPC, DWA, APF, Pure Pursuit etc.
GNU General Public License v3.0
2.29k stars 346 forks source link

bug fix and new function #78

Closed realhonbo closed 5 months ago

realhonbo commented 6 months ago

In some cases, developers cannot link Python to Python3，for example, when using ORB_SLAM2, explicitly using Python3 will not cause any errors. 2024-05-13 06-25-32 的屏幕截图

another issue is that: there is only a slight difference between the paths generated by RRT* and RRT , caused by this code 2024-05-15 00-21-01 的屏幕截图

realhonbo commented 5 months ago

For the official case, I just did two simple tests below： zzz5000 zzz1500 they got a similar path sample_points: quick-informed-rrt is 1500, informed-rrt is 5000 both sample_max_d and optimization_r are set to 50.0 time costs: informed-rrt is 1372ms, quick-informed-rrt is 236ms

more test data is needed !

ai-winter commented 5 months ago

@realHarvey

Thanks for your contribution, we will review the code later. Could you please provide the paper about quick-informed-rrt-star?

ai-winter commented 5 months ago

For the official case, I just did two simple tests below： zzz5000 zzz1500 they got a similar path sample_points: quick-informed-rrt is 1500, informed-rrt is 5000 both sample_max_d and optimization_r are set to 50.0 time costs: quick-informed-rrt is 1372ms, informed-rrt is 236ms

more test data is needed !

@realHarvey , why does the time cost of Quick-Informed-RRT turn out to be much higher than that of Informed-RRT? How does the QUICK aspect manifest itself?

realhonbo commented 5 months ago

@realHarvey

Thanks for your contribution, we will review the code later. Could you please provide the paper about quick-informed-rrt-star?

Im sorry about that，there is no paper anymore. Its just a part of my graduate article