Safety

Intelligent Mapping Solutions
AI-based Mapping solutions for Middle Mile.
Mar 4, 2025 8:20 AM 2025 WACV COOOL Challenge and Workshop
Aleksandr Petiushko Александр Петюшко
Slides
Intelligent Mapping Solutions
SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models
Integration of Position-Dependent Cross-Entropy loss function, Markov Logic Network, and Multimodal RAG with Vision Language Model (VLM), for achieving SotA results on Autonomous Driving benchmarks.
Jiawei Zhang, Xuan Yang, Taiqi Wang, Yu Yao, Aleksandr Petiushko Александр Петюшко, Bo Li
PDF Cite DOI arXiv
SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models
DiffScene: Diffusion-Based Safety-Critical Scenario Generation for Autonomous Vehicles
A guided diffusion-based scenario generation for safety-critical and realistic scenarios.
Chejian Xu, Aleksandr Petiushko Александр Петюшко, Ding Zhao, Bo Li
Cite Project
DiffScene: Diffusion-Based Safety-Critical Scenario Generation for Autonomous Vehicles
Middle Mile and Foundation Models
What is Middle Mile, and how it is related to Foundation Models, its advantages and challenges.
Sep 24, 2024 10:20 AM 2024 ITSC FMAD Workshop
Aleksandr Petiushko Александр Петюшко
Slides
Middle Mile and Foundation Models
Combining IMitation and Reinforcement Learning for Safe Autonomous Driving
The story of Nuro’s Research efforts in Planning // How to combine two distinct worlds - Imitation and Reinforcement Learning.
Jun 18, 2024 11:30 AM 2024 CVPR DDADS Workshop
Aleksandr Petiushko Александр Петюшко
Slides Video
Combining IMitation and Reinforcement Learning for Safe Autonomous Driving
CIMRL: Combining IMitation and Reinforcement Learning for Safe Autonomous Driving
A novel approach to bring two worlds - Imitation and Reinforcement Learning - together for Safe Planning.
Jonathan Booher, Khashayar Rohanimanesh, Junhong Xu, Aleksandr Petiushko Александр Петюшко
PDF Cite DOI arXiv
CIMRL: Combining IMitation and Reinforcement Learning for Safe Autonomous Driving
Multi-Constraint Safe RL with Objective Suppression for Safety-Critical Applications
A novel approach to tackle the multiple constraints challenge in Safe RL.
Zihan Zhou, Jonathan Booher, Wei Liu, Aleksandr Petiushko Александр Петюшко, Animesh Garg
PDF Cite arXiv SymposiumWeb
Multi-Constraint Safe RL with Objective Suppression for Safety-Critical Applications
Autonomous Driving: From Basics to Behavior Challenges
Overview of the Autonomy Stack and the problems of its Behavior side.
Jul 13, 2023 12:00 AM HSE Industrial Webinars
Aleksandr Petiushko Александр Петюшко
Slides Video
Autonomous Driving: From Basics to Behavior Challenges
Behavior Modeling and Learned Motion Selection for Safe Driving
The story of Nuro’s state-of-the-art research direction in motion prediction (Diffusion) and selection (Reinforcement Learning).
Jun 19, 2023 2:00 PM 2023 CVPR SSAD Workshop
Aleksandr Petiushko Александр Петюшко
Slides Video
Behavior Modeling and Learned Motion Selection for Safe Driving
Artificial Intelligence for Autonomous Driving
A panel discussion about the challenges and possible ways to solve it inside Autonomous Driving area.
Jun 6, 2023 11:00 AM 2023 IEEE CAI AI for AD Panel
Aleksandr Petiushko Александр Петюшко
Artificial Intelligence for Autonomous Driving