Category: Paper

Our recent preprint develops an architecture and a training method to give latent states physical meaning in the context of trajectory prediction:  

Zhen Lu, Imran Afridi, Hong Jin Kang, Ivan Ruchkin, Xi Zheng. Surveying Neuro-Symbolic Approaches for Reliable Artificial Intelligence of Things [Springer]. In Springer Journal of Reliable Intelligent Environments (JRIE), 2024.  Ankica Barišić, Jácome Cunha, Ivan Ruchkin, Ana Moreira, João Araújo, Moharram Challenger, Dušan Savić, Vasco Amaral. Modelling Sustainability in Cyber-Physical Systems: a Systematic Mapping Study [Elsevier]. In Elsevier Sustainable Computing:…

Our paper gives users of autonomous cars the ability to describe in natural language what conditions they consider nominal or anomalous. Citation: 

Our paper develops training-free world models based on foundation models with interpretable latent states. Update: presented at the probabilistic robotics workshop at ICRA’24. Citation: 

Our new draft verifies image-based controllers by approximating them with several low-dimensional ones. Citation:  Yuang Geng, Souradeep Dutta, Ivan Ruchkin. Bridging Dimensions: Confident Reachability for High-Dimensional Controllers [arxiv]. Preprint, in submission.

Update: a poster was presented at UF AI Days 2023. This paper develops safety chance prediction for image-controlled autonomous systems with calibration guarantees. Citation:  Zhenjiang Mao, Carson Sobolewski, Ivan Ruchkin. How Safe Am I Given What I See? Calibrated Prediction of Safety Chances for Image-Controlled Autonomy [arxiv]. Preprint, in submission.