GENESIS-RL: A Reinforcement Learning Framework for Generating Naturalistic Edge Cases to Systematically Test Autonomous Systems
GENESIS-RL leverages reinforcement learning to systematically manipulate the simulated environment and generate challenging yet naturalistic edge cases that can reveal potential safety vulnerabilities in autonomous systems.
UAS Target Search with Human-Centered Autonomy
인간 중심 자율성을 통한 UAS 타겟 검색의 효율적인 방법론 소개
Spatio-Temporal Overlap-Aware Multi-Sensor Calibration using Neural Radiance Fields
Neural Radiance Fields enable robust and accurate spatio-temporal multi-sensor calibration for autonomous systems.
Bayesian Methods for Trust in Collaborative Multi-Agent Autonomy Analysis
Bayesian trust estimation enhances security in multi-agent autonomy by mapping sensor data to trust pseudomeasurements.
CRPlace: Camera-Radar Fusion for Background-Attentive Place Recognition
CRPlace proposes a background-attentive camera-radar fusion method for accurate place recognition by focusing on stationary background features.
Safety-Aware Perception for Autonomous Collision Avoidance in Dynamic Environments
Autonomous collision avoidance is enhanced through a safety-aware perception algorithm that optimizes sensor-pointing direction using control barrier functions.
Visual Self-Supervised Traversability Learning for Off-road Navigation
Leveraging self-supervised learning and mask-based regularization improves traversability prediction in off-road environments.
3DGS-ReLoc: 3D Gaussian Splatting for Map Representation and Visual ReLocalization
Utilizing 3D Gaussian Splatting for accurate map representation and visual relocalization in autonomous systems.