Sampling-based Kinodynamic Planning with World Models
Sampling-based Kinodynamic Planning with World Models
This research presents a new method for motion planning using world models, where sampling-based strategies are applied to latent spaces to improve efficiency and success rates. The approach outperforms traditional optimizers like CEM and MP, achieving faster planning times and higher success rates in both simulated and real-world tasks.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Environment
- SimulationOpen source S4
Reported numbers
planning time
≤13.8
Reported success rate
20%
What remains unknown
Not established in the collected evidence: Control, Data origin.
Reported performance applies to the described task. It does not establish general autonomy or deployment readiness.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
ce, nearest-neighbor-guided RRT and projection-based KPIECE, with GPU-native batched expansion for efficient device utilization. We evaluate with an off-the-shelf DINO-WM on four simulated domains and a real-world block-pushing task. Our approaches match or exceed the success rate of CEM and MPPI at up to 13.8x lower planning time in simulation, and improve the success rate by 20% on the real robot.
Open source S4
Source：arXiv Robotics — research abstracts · arxiv.org