Stanford Intelligent and Interactive Autonomous Systems Group (ILIAD) develops algorithms for AI agents that safely and reliably interact with people. Our mission is to develop theoretical foundations for human-robot and human-AI interaction. Our group is focused on: 1) formalizing interaction and developing new learning and control algorithms for interactive systems inspired by tools and techniques from game theory, cognitive science, optimization, and representation learning, and 2) developing practical robotics algorithms that enable robots to safely and seamlessly coordinate, collaborate, compete, or influence humans.
Recent NewsCheck out our YouTube channel for latest talks and supplementary videos for our publications.
|Sep 21, 2023:||
Our 4 papers got accepted to the Conference on Neural Information Processing Systems (NeurIPS) 2023:
- Parallel Sampling of Diffusion Models (Spotlight)
- Diverse Conventions for Human-AI Collaboration
- Data Quality in Imitation Learning
- Inverse Preference Learning: Preference-based RL without a Reward Function
|Aug 30, 2023:||
Our 7 papers got accepted to the Conference on Robot Learning (CoRL) 2023:
- Stabilize to Act: Learning to Coordinate for Bimanual Manipulation (Oral)
- HYDRA: Hybrid Robot Actions for Imitation Learning
- Learning Sequential Acquisition Policies for Robot-Assisted Feeding
- Gesture-Informed Robot Assistance via Foundation Model
- KITE: Keypoint-Conditioned Policies for Semantic Manipulation
- Large Language Models as General Pattern Machines
- Polybot: Training One Policy Across Robots While Embracing Variability
|Apr 24, 2023:||
Our 4 papers got accepted to the International Conference on Machine Learning (ICML) 2023:
- "Language Instructed Reinforcement Learning for Human-AI Coordination"
- "Generating Language Corrections for Teaching Physical Control Tasks"
- "Distance Weighted Supervised Learning: Robust Learning From Offline Interaction Data"
- "Long Horizon Temperature Scaling"
|Apr 24, 2023:||
Our 2 papers got accepted to the Proceedings of Robotics: Science and Systems (RSS) 2023:
- "Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasets"
- "Language-Driven Representation Learning for Robotics"
|Jan 30, 2023:||Our paper titled "Reward Design with Language Models" got accepted to the International Conference on Learning Representations (ICLR)!|