Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 16, 2025Open Access

Dynamic Risk-Aware MPPI for Mobile Robots in Crowds via Efficient Monte Carlo Approximations

View Full Paper
Ask AI
Bookmark
Share

Authors

ETElia TrevisanDelft University of TechnologyKMKhaled A. MustafaDelft University of TechnologyGNGodert Notten

Discussion

Loading...

Member takes

Implication

Proposed Dynamic Risk-Aware Model Predictive Control improves safety in mobile robots, indicating more effective trajectory planning across variable obstacles.

Key Points

  • DRA-MPPI enhances safety for mobile robots navigating among multiple dynamic obstacles and significantly reduces collision risks.
  • Real-time approximations of joint Collision Probability are achieved using a Monte Carlo approach on hundreds of sampled trajectories.
  • The method overcomes the freezing robot problem while demonstrating superior performance against existing state-of-the-art planning techniques.
  • Integration of uncertain, non-Gaussian predictions in decision-making optimizes navigation under dynamic conditions.

Cite This Study

Trevisan et al. (2025) studied this question.

synapsesocial.com/papers/68f04acce559138a1a06e7bbhttps://doi.org/10.48550/arxiv.2506.21205
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Integrating Predictive Motion Uncertainties with Distributionally Robust Risk-Aware Control for Safe Robot Navigation in Crowds2024
  2. 2Decentralized Uncertainty-Aware Multi-Agent Collision Avoidance with Model Predictive Path Integral2025
  3. 3BC-MPPI: A Probabilistic Constraint Layer for Safe Model-Predictive Path-Integral Control2025
  4. 4Path Integral Control with Rollout Clustering and Dynamic Obstacles2024
  5. 5Differential Dynamic Programming-based Path Planning and Control Using Stochastic Initialization2026