Student Talks
Open-World Policy Steering for Robot Manipulation
Abstract: Generative robot policies have shown remarkable potential in learning complex, multimodal behaviors from demonstrations. However, at runtime, they still exhibit diverse failures ranging from task incompletion (e.g., toppling or dropping objects) to misaligned behaviors (e.g., placing the gripper inside of a cup of water). Instead of constantly re-training the policies with new data, we [...]
Deep 3D Geometric Reasoning for Robot Manipulation
Abstract: To solve general manipulation tasks in real-world environments, robots must be able to perceive and condition their manipulation policies on the 3D world. These agents will need to understand various common-sense spatial/geometric concepts about manipulation tasks: that local geometry can suggest potential manipulation strategies; that changes in observation viewpoint shouldn't affect the interpretation of [...]
Deformation-Aware Manipulation: Compliant and Geometric Approaches for Non-Anthropomorphic Hands
Abstract: Soft robot hands offer compelling advantages for manipulation tasks, including inherent safety through material compliance, robust adaptation to uncertain object geometries, and the ability to conform to complex shapes passively. However, these same properties create significant challenges for conventional sensing and control approaches. This talk presents approaches to bridging advances in geometric learning and [...]
Towards Natural Language-Driven Shape Arrangement Synthesis using Semantically-Aware Geometric Constraints
Abstract: While diffusion-based models excel at generating photorealistic images from text, a more nuanced challenge emerges when constrained to using only a fixed set of rigid shapes—akin to solving tangram puzzles or arranging real-world objects to match semantic descriptions. We formalize this problem as shape-based image generation, a new natural language-guided image-to-image translation task that [...]
Toward Generalizable Interaction-aware Human Motion Prediction
Abstract: As autonomous robots are increasingly expected to operate in dynamic, human-centered environments, it is crucial to develop robot policies that ensure safe and seamless interactions with humans, all while allowing robots to complete their intended tasks efficiently. To achieve this, robots must be capable of making informed decisions that account for human preferences, ensuring [...]
Enhancing Reinforcement Learning with Error-Prone Language Models
The correct specification of reward models is a well-known challenge in reinforcement learning. Hand-crafted reward functions, which are usually sparse, often lead to inefficient or suboptimal policies, misalignment with user values, or difficulties in attributing credit or blame within multi-agent systems. Reinforcement learning from human feedback is a successful technique that can mitigate such issues [...]
Efficient Multi-Agent Motion Planning using Local Policies
Abstract: Teams of multiple robots working together can achieve challenging tasks like warehouse automation, search and rescue, and cooperative construction. However, finding efficient collision-free motions for all agents is extremely challenging as the complexity of the multi-agent motion planning (MAMP) problem grows exponentially with the number of agents. Multi-Agent Path Finding (MAPF) is a subset [...]
Foundation Control Model for General Embodied Intelligence
Abstract: With the growing accessibility of humanoid hardware and rapid advances in foundation models, we are entering an era where achieving general embodied intelligence is within reach—enabling humanoid robots to perform a wide range of tasks in human-centric environments. Despite significant progress in language and vision foundation models, controlling humanoids with high degrees of freedom [...]
Learning Humanoid Robots from Simulation to Real to Simulation
Abstract: How do we teach humanoid robots to move like humans—and do so reliably in the real world? In this talk, I’ll share my journey in building a learning-based pipeline that closes the loop between simulation and reality for humanoid whole-body control. Starting from real-time teleoperation (H2O), to scalable data humanoid collection (OmniH2O), to learning [...]
Experience-Based Action Advising for Multi-Agent Teaming
Abstract: We study how to improve coordination efficiency for multi-agent teams with heterogeneously experienced agents. In such a setting, experienced agents can transfer their knowledge to less experienced agents to accelerate their learning, while leveraging the students' initial expertise to inform what knowledge to transfer. Inspired by this idea, this work specifically assumes one teacher [...]