Search papers, labs, and topics across Lattice.
6
0
7
6
A new SF-GVF with prescribed physical speed (PPS) that converge exponentially to the desired path from any initial condition in the higher-dimensional space (including virtual dimension); more importantly, the robot's physical speed converges to the PPS, while the path-error dynamics remain invariant under regular reparameterizations of the desired path.
SkillGuard cuts attack success rates to as low as 4.8% by redefining agent capabilities in response to contamination from untrusted data.
Trust in AI-driven decisions can be systematically documented, ensuring accountability at the crucial output-to-action boundary in bioscience research.
Achieving finite-time convergence in nonholonomic robots without compromising actuator limits could redefine motion planning strategies in robotics.
Adversaries can achieve up to 88.2% success in exploiting LLMs for log analysis through passive prompt injection, highlighting a critical security vulnerability.
Achieving simultaneous arrival for multi-robot systems with curvature and speed constraints could revolutionize cooperative tasks in dynamic environments.
