Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 20, 2025Open Access

GUARD: Toward a Compromise between Traditional Control and Learning for Safe Robot Systems

View Full Paper
Ask AI
Bookmark
Share

Authors

JGJohannes A. GausJYJunheon YoonWBWoo-Jeong Baek

Discussion

Loading...

Member takes

Overview

Framework GUARD improves collision avoidance in robots, suggesting a blend of control methods enhances safety.

Key Points

  • GUARD achieves efficient robot collision avoidance through the integration of control and learning methods.
  • Experimental studies show high performance in collision avoidance using the GUARD framework for real-time processing.
  • The method combines reactive model predictive contouring control and Iterative Closest Point for uncertainty management.
  • This unified approach addresses the ambiguity of safety in robotics, indicating its potential for broader applications.

Cite This Study

Gaus et al. (2025) studied this question.

synapsesocial.com/papers/68f6196ee0bbbc94fac36586https://doi.org/10.48550/arxiv.2509.23312
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. 1Safety-Critical Control with Uncertainty Quantification using Adaptive Conformal Prediction2024
  2. 2Predictive Safety in Reinforcement Learning2026
  3. 3Integrating Predictive Motion Uncertainties with Distributionally Robust Risk-Aware Control for Safe Robot Navigation in Crowds2024
  4. 4A Safety-Critical Framework for UGVs in Complex Environments: A Data-Driven Discrepancy-Aware Approach2024
  5. 5Uncertainty Aware-Predictive Control Barrier Functions: Safer Human Robot Interaction through Probabilistic Motion Forecasting2025