This paper introduces a nonlinear, actuator-aware safety filter for 3D Gaussian Splatting (3DGS) based on full quadrotor dynamics, reducing trajectory jerk by 47% and running 2.25 times faster than ex…

The paper introduces TouchSafeBench, a physics-grounded benchmark, to evaluate collision grounding—the ability to predict robot-human collisions—and finds that current Vision-Language Models (VLMs) ar…

This paper evaluates the integration of Language Model Machines (LLMs) into control tasks in automotive contexts from a safety assurance perspective, identifying conceptual and concrete challenges.

This paper analyzes incidents involving autonomous vehicles (AVs) and identifies gaps in current safety paradigms, suggesting the need for human-interactive autonomy.

This paper evaluates two approaches for maintaining safe separation between small Unmanned Aircraft Systems (sUAS) in urban environments with degraded Global Navigation Satellite System (GNSS) signals…

This paper proposes a Fisher information density (FID)-constrained trajectory sharing scheme for robot collision avoidance under GDPR regulations, achieving better privacy-utility tradeoff than fixed-…

PhyGenHOI introduces a novel framework that generates physically accurate and visually faithful 4D Human-Object Interactions by coupling generative human motion with explicit physical object simulatio…

SARAD proposes a novel safety-aware hybrid framework that combines Large Language Models (LLMs) and Deep Reinforcement Learning (DRL) to improve autonomous driving decision-making by replacing random…

The paper develops a novel deep reinforcement learning framework, SMamba-DDPG, to accurately model vehicle-type-specific pedestrian crash avoidance behavior, finding that pedestrians react faster and…

The paper proposes CPGAN, a novel Generative Adversarial Network (GAN) that incorporates a collision-penalizing loss function to significantly improve the simulation of collision avoidance in dense, b…

This paper presents CARLA-GS, a modular corner-case synthesis pipeline for autonomous driving that decouples visual representation, semantic reasoning, and physics-based execution while maintaining ti…

This paper proposes novel high-order control barrier functions and a high-order control Lyapunov function for the optimal safety control problem of nonlinear control systems.

The paper proposes CARA, an interpretable framework for collision anticipation in autonomous driving using domain-grounded risk concepts, aligning them with video frames, and organizing them into evol…

This paper provides a comprehensive review of network optimization aspects for Connected and Autonomous Vehicles (CAVs), aiming to clarify misconceptions and outline future research directions.

This paper demonstrates that reasoning-enabled Vision-Language-Action (VLA) models for autonomous driving are highly vulnerable to realistic input perturbations, significantly compromising both reason…

The paper proposes a multi-resolution end-to-end deep neural network for autonomous driving that dynamically adjusts input resolution to optimize the critical tradeoff between prediction accuracy and…

The paper analyzes the algorithmic complexity of finding collisions in single-layer binary neural networks, establishing that the collision resistance depends critically on the activation function's t…

The paper introduces TWGuard, a linguistic context-optimized safety guardrail model, demonstrating that tailoring AI safety mechanisms to specific local linguistic contexts significantly improves perf…