all AI news
Collision Avoidance Verification of Multiagent Systems with Learned Policies
March 7, 2024, 5:42 a.m. | Zihao Dong, Shayegan Omidshafiei, Michael Everett
cs.LG updates on arXiv.org arxiv.org
Abstract: For many multiagent control problems, neural networks (NNs) have enabled promising new capabilities. However, many of these systems lack formal guarantees (e.g., collision avoidance, robustness), which prevents leveraging these advances in safety-critical settings. While there is recent work on formal verification of NN-controlled systems, most existing techniques cannot handle scenarios with more than one agent. To address this research gap, this paper presents a backward reachability-based approach for verifying the collision avoidance properties of Multi-Agent …
abstract advances arxiv capabilities collision control cs.lg cs.ma cs.ro cs.sy eess.sy however networks neural networks nns robustness safety safety-critical systems type verification work
More from arxiv.org / cs.LG updates on arXiv.org
Testable Learning with Distribution Shift
1 day, 10 hours ago |
arxiv.org
Quantum circuit synthesis with diffusion models
1 day, 10 hours ago |
arxiv.org
Fitness Approximation through Machine Learning
1 day, 10 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Seeking Developers and Engineers for AI T-Shirt Generator Project
@ Chevon Hicks | Remote
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Stage - Product Owner Assistant - Data Platform / Business Intelligence (M/F)
@ Pernod Ricard | FR - Paris - The Island