Research map / Optimization / Optimizers
Accelerating Motion Planning via Optimal Transport
An Thai Le, Georgia Chalvatzaki, Armin Biess, Jan Peters
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use MPOT instead of CHOMP | trajectory optimizer · Panda (dense clutter) | success rate SUC [%]: 63.0 -> 71.6 | Improved |
| use MPOT instead of SGPMP | trajectory optimizer · Panda (dense clutter) | planning time T [s]: 5.0 -> 0.8 | Improved |
| use MPOT instead of GPMP2 | trajectory optimizer · Point-mass (dense clutter) | planning time T [s]: 2.8 -> 0.4 | Improved |
| use MPOT instead of CHOMP | trajectory optimizer · Point-mass (dense clutter) | success rate SUC [%]: 70.9 -> 99.2 | Improved |
| use MPOT instead of SGPMP | trajectory optimizer · Point-mass (dense clutter) | GOOD [%]: 74.9 -> 73.6 | No clear effect |
| use MPOT instead of GPMP2 | trajectory optimizer · Point-mass (dense clutter) | smoothness S: 0.07 -> 0.06 | No clear effect |
| use MPOT instead of RRT* | sampling planner · Panda (dense clutter) | planning time T [s]: 186.9 -> 0.8 | Improved |
| use MPOT instead of CHOMP | trajectory optimizer · Mobile fetch & place (TIAGo++) | time to first solution TF [s]: 16.74 -> 1.49 | Improved |
| use MPOT instead of GPMP2 | trajectory optimizer · Mobile fetch & place (TIAGo++) | success rate SUC [%]: 40 -> 55 | Improved |
| use MPOT instead of SGPMP | trajectory optimizer · Mobile fetch & place (TIAGo++) | smoothness S: 0.010 -> 0.022 | Hurt |
| use MPOT instead of SGPMP | trajectory optimizer · Mobile fetch & place (TIAGo++) | path length PL: 6.69 -> 10.53 | Hurt |
| add step radius annealing (ablation) | MPOT · Panda convergence | cost convergence speed | Improved |
Closest papers by meaning
- BaB-ND: Long-Horizon Motion Planning with Branch-and-Bound and Neural Dynamics (ICLR 2025 · similarity 0.86)
- Potential Based Diffusion Motion Planning (ICML 2024 · similarity 0.86)
- Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous and Instruction-guided Driving (CVPR 2024 · similarity 0.85)
- Model-based Diffusion for Trajectory Optimization (NeurIPS 2024 · similarity 0.85)
- Physics-informed Temporal Difference Metric Learning for Robot Motion Planning (ICLR 2025 · similarity 0.85)
- Simultaneous Multi-Robot Motion Planning with Projected Diffusion Models (ICML 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
