AURA: Asymptotically Optimal Uncertainty-Robust Replanning Algorithm

1. 04:00
   arXiv Robotics — research abstracts

   Real-Time Motion Planning in Dynamic Environments

   Study compares classical and learning-based methods in real-time motion planning. Results show learning-based approaches outperform in stochastic settings due to uncertainty in obstacle dynamics.

2. 04:00
   arXiv Robotics — research abstracts

   AURA: Asymptotically Optimal Uncertainty-Robust Replanning Algorithm for Kinodynamic Systems

   AURA is a meta-planner framework that enhances path quality and tracking performance during execution for kinodynamic systems. It integrates online replanning and optimization to reduce tracking error under motion uncertainty, demonstrating improvements in trajectory quality and performance across simulations and real-world environments.

Current attention 4·Peak within the comparable range 4（2026-10-10 11:00 UTC）·Change within the comparable range over 24 hours –

The trend compares participants observed continuously; its scope may be narrower than current attention totals. Hover or click to explore hourly observations, or use the left and right arrow keys.