Schedule (tentative)
8:55 - 9:00
Introductory Remarks
9:00 - 9:30
Tentative talk title: Evolutionary design of morphology and control for simulated and real-world robots
9:30 - 10:00
Tentative talk title: Cooperative Human-AI Robot Design and Synthesis
10:00 - 10:30
Tentative talk title: Embodied AI Generalization Strategies
10:30 - 11:00: Break
11:00 - 11:15
Lightning Talks
ECoDe: A Sample-Efficient Method for Co-Design of Robotic Agents
RoboNet: A Sample-Efficient Robot Co-Design Generator
Minimally Invasive Morphology Adaptation via Parameter Efficient Fine-Tuning
Overcoming State and Action Space Disparities in Multi-Domain, Multi-Task Reinforcement Learning
One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion
Making use of design-aware policy optimization in legged-robotics co-design
MAC: Morphology-Aware Control Design with Deep Reinforcement Learning for Navigation of Squeezable Unmanned Aerial Vehicles
Grammarization-based Multi-Morphology and Multi-Target Grasping via Reinforcement Learning in the Latent Space of Autoencoders
11:15 - 11:30
Best Paper Talks
11:15 - 11:20 Best Machine Learning Paper Award: Dynamics-Guided Diffusion Model for Sensor-less Robot Manipulator Design
11:20 - 11:25 Best Robotics Paper Award: D(R,O) Grasp: A Unified Representation of Robot and Object Interaction for Cross-Embodiment Dexterous Grasping
11:25 - 11:30 Best Evolutionary Robotics Paper Award: Parental Guidance: Efficient Lifelong Learning through Evolutionary Distillation
11:30 - 12:00
Poster Session
12:00 - 2:00: Lunch
2:00 - 2:30
Tentative talk title: Learning Generalizable Policies from Extreme Cross-Embodiment Data
2:30 - 3:00
Tentative talk title: Morphology-Agnostic Policy Learning: Past, Present, and Future Directions
3:00 - 3:30
Tentative talk title: Embodied Multimodal Intelligence with Foundation Models
3:30 - 4:00: Break
4:00 - 5:00
Poster Session
5:00 - 6:00