CS269: Interactive Robot Learning (fall 2025)

Schedule

Date	Topic	Readings	Deadline
Week 1 Mon, Sep 29	Course Logistics	(no reading)	Sign up for paper presentations!
Week 1 Wed, Oct 1	Robot Learning Foundations & How to Read Papers	Human-Interactive Robot Learning: Definition, Challenges, and Recommendations The Bitter Lesson (Rich Sutton) Why Today’s Humanoids Won’t Learn Dexterity (Rodney Brooks)	Quiz responses due the day of class at midnight.
Week 2 Mon, Oct 6	Task and Motion Planning	Guiding Long-Horizon Task and Motion Planning with Vision Language Models VLMgineer: Vision Language Models as Robotic Toolsmiths Open-World Task and Motion Planning via Vision-Language Model Inferred Constraints	Quiz questions due 2 days before class at midnight. Quiz responses due the day of class at midnight.
Week 2 Wed, Oct 8	Generalizable Motion Generation	Language Models as Zero-Shot Trajectory Generators Deep Reactive Policy: Learning Reactive Manipulator Motion Planning for Dynamic Environments DEXTERITYGEN: Foundation Controller for Unprecedented Dexterity	Quiz questions due 2 days before class at midnight. Quiz responses due the day of class before 9am.
Week 3 Mon, Oct 13	Representation Learning	OpenVLA: An Open-Source Vision-Language-Action Model Deceptive Risk Minimization: Out-of-Distribution Generalization by Deceiving Distribution Shift Detectors STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy Learning	Quiz questions due 2 days before class at midnight. Quiz responses due the day of class before 9am.
Week 3 Wed, Oct 15	Guest Lecture, Speaker: Anushri Dixit	(no reading)	Project Proposal due Oct 18 at 11:59PM
Week 4 Mon, Oct 20	Reinforcement Learning & Reward Design	Scaffolding Dexterous Manipulation with Vision-Language Models ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics ReWiND: Language-Guided Rewards Teach Robot Policies without New Demonstrations	Quiz questions due 2 days before class at midnight. Quiz responses due the day of class before 9am.
Week 4 Wed, Oct 22	Behavior Cloning	Diffusion Policy: Visuomotor Policy Learning via Action Diffusion Streaming Flow Policy: Simplifying diffusion/flow-matching policies by treating action trajectories as flow trajectories SAIL: Faster-than-Demonstration Execution of Imitation Learning Policies	Quiz questions due 2 days before class at midnight. Quiz responses due the day of class before 9am.
Week 5 Mon, Oct 27	Shared Autonomy	To the Noise and Back: Diffusion for Shared Autonomy Conformalized Teleoperation: Confidently Mapping Human Inputs to High-Dimensional Robot Actions Fleet-DAgger: Interactive Robot Fleet Learning with Scalable Human Supervision	Quiz questions due 2 days before class at midnight. Quiz responses due the day of class before 9am.
Week 5 Wed, Oct 29	Learning from Human Data	OKAMI: Teaching Humanoid Robots Manipulation Skills through Single Video Imitation Phantom: Training Robots Without Robots Using Only Human Videos DemoDiffusion: One-Shot Human Imitation using pre-trained Diffusion Policy	Quiz questions due 2 days before class at midnight. Quiz responses due the day of class before 9am.
Week 6 Mon, Nov 3	Communication	CoRI: Synthesizing Communication of Robot Intent for Physical Human-Robot Interaction Latent Theory of Mind: A Decentralized Diffusion Architecture for Cooperative Manipulation Cross-Modality Embedding of Force and Language for Natural Human-Robot Communication	Quiz questions due 2 days before class at midnight. Quiz responses due the day of class before 9am.
Week 6 Wed, Nov 5	[project elevator pitch presentations]	(no reading)	Project Milestone Review due Nov 8 at 11:59PM
Week 7 Mon, Nov 10	Multi-Modal Interaction - I	Vision in Action: Learning Active Perception from Human Demonstrations FEAST: A Flexible Mealtime-Assistance System Tackling In-the-Wild Personalization The Sound of Simulation: Learning Multimodal Sim-to-Real Robot Policies with Generative Audio	Quiz questions due 2 days before class at midnight. Quiz responses due the day of class before 9am.
Week 7 Wed, Nov 12	Multi-Modal Interaction - II	NOIR: Neural Signal Operated Intelligent Robots for Everyday Activities First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization Tactile Beyond Pixels: Multisensory Touch Representations for Robot Manipulation	Quiz questions due 2 days before class at midnight. Quiz responses due the day of class before 9am.
Week 8 Mon, Nov 17	Scaling Interactive Learning	RaC: Robot Learning for Long-Horizon Tasks by Scaling Recovery and Correction EgoMimic: Scaling Imitation Learning via Egocentric Video Steering Your Diffusion Policy with Latent Space Reinforcement Learning	Quiz questions due 2 days before class at midnight. Quiz responses due the day of class before 9am.
Week 8 Wed, Nov 19	Lifelong and Continual Robot Learning	Fast Lifelong Adaptive Inverse Reinforcement Learning from Demonstrations LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discovery A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics	Quiz questions due 2 days before class at midnight. Quiz responses due the day of class before 9am.
Week 9 Mon, Nov 24	Lecture	Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgetting OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction
Week 9 Wed, Nov 26	break
Week 10 Mon, Dec 1	Final project presentations
Week 10 Wed, Dec 3	Final project presentations		Project report due Dec 5 at 11:59PM (firm).

Additional resources:

• CS 391R: Robot Learning (UT Austin)
• CS 237B: Principles of Robot Autonomy II
• CSCI 699: Robot Learning (USC)