← Back to the feed
Robotics & manufacturingResearch findings

CoopUQ · Proposal of a Cooperative Prediction Framework for Multi-Robot Social Navigation with Uncertainty Awareness

Original published 2026.10.20 02:59 KSTAdded to Blackdeck 2026.10.20 23:53 KST

What has changed?

Fuses spatiotemporal features across robots to perform uncertainty-aware occupancy prediction

Key points

  1. Proposes a cooperative prediction framework for multi-robot social navigation with uncertainty awareness
  2. Integrates uncertainty-aware occupancy forecasting with constrained multi-agent reinforcement learning
  3. Improves safety and efficiency under occlusions and out-of-distribution scenarios

Connect it to your work

Adjusts navigation policy based on predicted occupancy and uncertainty levels

What remains unproven

The abstract reports simulation results; real-world performance is not established by this input.

Originals used for this note

Links open the original publisher in a new tab.

  1. arxivCoopUQ: Robust Multi-Robot Social Navigation via Uncertainty-Aware Cooperative Forecasting