6 papers · 1 filter
Inspect Robots: Evaluating the Capabilities and Safety of Embodied AI
Christopher Leet, Achu Menon, Sravanthi Machcha +12
General purpose language models are increasingly able to control robotic hardware. Understanding the capabilities and safety of these models when embodied is therefore increasingly…
MAD-PINN: A Decentralized Physics-Informed Machine Learning Framework for Safe and Optimal Multi-Agent Control
Manan Tayal, Aditya Singh, Shishir Kolathaya +1
Co-optimizing safety and performance in large-scale multi-agent systems remains a fundamental challenge. Existing approaches based on multi-agent reinforcement learning (MARL), saf…
Neural Control Barrier Functions from Physics Informed Neural Networks
Shreenabh Agrawal, Manan Tayal, Aditya Singh +1
As autonomous systems become increasingly prevalent in daily life, ensuring their safety is paramount. Control Barrier Functions (CBFs) have emerged as an effective tool for guaran…
A Physics-Informed Machine Learning Framework for Safe and Optimal Control of Autonomous Systems
Manan Tayal, Aditya Singh, Shishir Kolathaya +1
As autonomous systems become more ubiquitous in daily life, ensuring high performance with guaranteed safety is crucial. However, safety and performance could be competing objectiv…
Semi-Supervised Safe Visuomotor Policy Synthesis using Barrier Certificates
Manan Tayal, Aditya Singh, Pushpak Jagtap +1
In modern robotics, addressing the lack of accurate state space information in real-world scenarios has led to a significant focus on utilizing visuomotor observation to provide sa…
Exact Imposition of Safety Boundary Conditions in Neural Reachable Tubes
Aditya Singh, Zeyuan Feng, Somil Bansal
Hamilton-Jacobi (HJ) reachability analysis is a widely adopted verification tool to provide safety and performance guarantees for autonomous systems. However, it involves solving a…