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

Key points

• Rather than introducing a new planner, we construct a unified benchmark in which representative classical and learning-based methods face the same environments, motion constraints, information assumptions, and evaluation metrics.1
• The test environment consists of planar domains populated with rotating sprinkler-like hazards that generate time-varying forbidden regions via sweeping angular sectors.1
• Under stochastic obstacle dynamics, however, online search becomes strongly budget-sensitive: low budgets lead to frequent failure, while high budgets improve success at the cost of latency and longer trajectories.1
• PPO-based policies, trained under the same scenario distribution, consistently outperform in latency, success rate, and path quality in these stochastic regimes.1

Sources (1)

• [1]Real-Time Motion Planning with Dynamic Hazards: Classical vs. Learning-Based Methods
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 04:24 PM

  We study real-time motion planning in dynamic hazard fields through a controlled comparison between classical planning and learning-based methods.

  Rather than introducing a new planner, we construct a unified benchmark in which representative classical and learning-based methods face the same environments, motion constraints, information assumptions, and evaluation metrics.

Extractive summary: sentences quoted from the sources.