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.
|Jan 31, 2022:||
Our 4 paper got accepted at International Conference on Robotics and Automation (ICRA) 2022:
- "Balancing Efficiency and Comfort in Robot-Assisted Bite Transfer"
- "Learning from Imperfect Demonstrations via Adversarial Confidence Transfer"
- "Weakly Supervised Correspondence Learning"
- "Leveraging Smooth Attention Prior for Multi-Agent Trajectory Prediction"
|Jan 6, 2022:||
Our 2 papers got accepted at the 17th ACM/IEEE International Conference on Human-Robot Interaction (HRI):
- "APReL: A Library for Active Preference-based Reward Learning Algorithms" by Biyik et al.
- "Conditional Imitation Learning for Multi-Agent Games" by Shih et al.
|Dec 16, 2021:||
Our 2 papers got accepted at the 36th AAAI Conference on Artificial Intelligence:
- "PantheonRL: A MARL Library for Dynamic Training Interactions" by Sarkar et al.
- "Partner-Aware Algorithms in Decentralized Cooperative Bandit Teams" by Biyik et al.
|Sep 28, 2021:||Our paper titled "ELLA: Exploration through Learned Language Abstraction" got accepted to Conference on Neural Information Processing Systems (NeurIPS)!|
|Sep 28, 2021:||Our paper titled "Confidence-Aware Imitation Learning from Demonstrations with Varying Optimality" got accepted to Conference on Neural Information Processing Systems (NeurIPS)!|