← Back to all news
arXiv AI

Real-Time Motion Planning with Dynamic Hazards: Classical vs. Learning-Based Methods

The paper compares classical motion planners with learning-based methods for real-time navigation in environments with dynamic hazards, using a unified benchmark that includes identical settings and metrics. In deterministic scenarios, classical planners achieve near-perfect success and high-quality paths, though they can incur significant planning time. When obstacle dynamics are stochastic, classical planners become highly budget-sensitive, whereas PPO-trained policies consistently deliver better latency, success rates, and path quality.

Related stories

arXiv Machine Learning
4d ago

Planning under Noise with Neural Operators

The paper introduces Planning Under Noise (PUN), a neural operator that learns noise‑aware value fields for planning in unseen geometries. By imposing reflecting Neumann conditions on obstacles and a Dirichlet condition at the goal, PUN allows sampled paths to explore free space until reaching the target. It extends the Monte Carlo solver Walk on Stars to higher dimensions, learns geometry‑to‑field mappings from noisy labels, and achieves high success rates and low runtimes on 4‑D replanning benchmarks across multiple noise levels.

By Michael Chen, Hong Chul Nam, Xi Deng, Anima Anandkumar
benchmarks
More like this →
arXiv Machine Learning
Oct 3

Training-Free Diffusion Planning with Analytical Local Scores

The paper presents a training-free diffusion-based motion planner that replaces learned global trajectory scores with analytical local scores derived from obstacle, smoothness, velocity, and inter-agent feasibility terms. By reconstructing trajectory scores through local interactions between neighboring waypoints and nearby constraints, the method decomposes the denoising process while preserving the optimization structure of classical trajectory methods. Experiments demonstrate that this approach generates smooth, feasible trajectories for large multi-agent tasks in complex environments quickly, outperforming learning-based and optimization baselines without requiring training data.

By Michael Y. Fatemi, Jinhao Liang, Ferdinando Fioretto
agentsdiffusionroboticsmultimodal
More like this →
arXiv AI
Aug 19

Dijkstra as an Oracle for Online Stochastic Shortest Path Navigation with Provable Guarantees

The paper presents DORA, an online learning algorithm for robot navigation that uses Dijkstra’s algorithm as an exact planning engine under a weaker condition than usual causality—specifically, nonnegativity of a reduced cost on a determinized map. DORA calls a shortest‑path oracle a fixed number of times per episode, avoids estimating transition kernels, and incorporates a logarithmic survival weight to keep contact probabilities with dynamic obstacles within a budget. Experiments on grid‑world, directional drilling, and drone surveillance benchmarks show that DORA matches optimistic value iteration with the true transition kernel while performing 4.5 to 19.3 times less planner work, reduces contacts by a factor of seventeen compared to determinize‑and‑replan, and maintains contact rates within wide budget ranges.

By Mansur M. Arief, Ali Akarma, Ahmad Alfan Alfian Irfan
roboticsbenchmarks
More like this →
arXiv Statistics ML
Oct 1

Learning to Plan from Random Exploration

arXiv:2609.38383v1 Announce Type: cross Abstract: Random exploration reveals how an environment can be traversed before a goal is specified. Can this experience support long-range planning without po...

By Deqian Kong, Guangyan Sun, Sheng Cheng, Sirui Xie, Bo Pang, Jianwen Xie, Tony Geng, Caiwen Ding, Ying Nian Wu
ragagentsdiffusionrobotics
More like this →