Embodied systems are playing an increasingly important role in our lives. Examples include, but are not limited to, autonomous driving, drone delivery, and service robots. In real-world deployments, the systems are required to safely learn and operate under the various sources of uncertainties. As noted in the “Roadmap for US Robotics (2020)”, safe learning and adaptation is a key aspect of next-generation robotics. Learning is ingrained in all components of the robotics software stack including perception, planning, and control. While the safety and robustness of these components have been identified as critical aspects for real-world deployments, open issues and challenges are often discussed separately in the respective communities. In this workshop, we aim to bring together researchers from machine learning, computer vision, robotics, and control to facilitate interdisciplinary discussions on the topic of deployable decision making in embodied systems. Our workshop will focus on two discussion themes: (i) safe learning and decision making in uncertain and unstructured environments and (ii) efficient transfer learning for deployable embodied systems. To facilitate discussions and solicit participation from a broad audience, we plan to have a set of interactive lecture-style presentations, focused discussion panels, and a poster session with contributed paper presentations. By bringing researchers and industry professionals together in our workshop and having detailed pre- and post-workshop plans, we envision this workshop to be an effort towards a long-term, interdisciplinary exchange on this topic.
| Opening Remarks & Introduction (Live Introduction) | |
| Reinforcement Learning in Real-World Control Systems (Invited Talk) | |
| Deployable Robot Learning with Self-supervised Spatial Action Maps (Invited Talk) | |
| Learning Abstractions for Robust and Tractable Planning (Invited Talk) | |
| Learning Closed-form Control Law for Adaptive and Fast Decision (Invited Talk) | |
| Coffee Break (Break) | |
| Panel A: Deployable Learning Algorithms for Embodied Systems (Panel Discussion) | |
| Spotlight Talk Introduction (Spotlight) | |
| Spotlights (Spotlight) | |
| Evaluation as a Process for Engineering Responsibility in AI (Invited Spotlight) | |
| Poster Session | |
| Theme B Introduction (Introduction) | |
| Robust Embedded Learned Models (Invited Talk) | |
| Human-in-the-loop Bayesian Deep Learning (Invited Talk) | |
| Learning for Agile Control in the Real World: Challenges and Opportunities (Invited Talk) | |
| Enforcing Robustness for Neural Network Policies (Invited Talk) | |
| Coffee Break (Break) | |
| Panel B: Safe Learning and Decision Making in Uncertain and Unstructured Environments (Panel Discussion) | |
| Concluding Remarks (Conclusion) | |
| Post-Workshop Social Event (Social Event) | |
| 3D Neural Scene Representations for Visuomotor Control (Poster) | |
| 3D Neural Scene Representations for Visuomotor Control (Spotlight) | |
| Safe Evaluation For Offline Learning: \\Are We Ready To Deploy? (Poster) | |
| ilpyt: Imitation Learning Research Code Base in PyTorch (Poster) | |
| Equidistant Hyperspherical Prototypes Improve Uncertainty Quantification (Poster) | |
| Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning (Poster) | |
| Vision-Guided Quadrupedal Locomotion in the Wild with Multi-Modal Delay Randomization (Poster) | |
| Towards Safe Global Optimality in Robot Learning with GoSafe (Poster) | |
| Learning Impedance Actions for Safe Reinforcement Learning in Contact-Rich Tasks (Poster) | |
| Extraneousness-Aware Imitation Learning (Poster) | |
| Look Closer: Bridging Egocentric and Third-Person Views with Transformers for Robotic Manipulation (Poster) | |
| Deep Reinforcement Learning Policies for Underactuated Satellite Attitude Control (Poster) | |
| GRILC: Gradient-based Reprogrammable Iterative Learning Control for Autonomous Systems (Poster) | |
| A Unified Approach to Obstacle Avoidance and Motion Learning (Poster) | |
| Safe Evaluation For Offline Learning: \\Are We Ready To Deploy? (Spotlight) | |
| What Would the Expert $do(\cdot)$?: Causal Imitation Learning (Poster) | |
| Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers (Spotlight) | |
| Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers (Poster) | |
| Validate on Sim, Detect on Real - Model Selection for Domain Randomization (Spotlight) | |
| Validate on Sim, Detect on Real - Model Selection for Domain Randomization (Poster) | |
| Zero-Shot Uncertainty-Aware Deployment of Simulation Trained Policies on Real-World Robots (Spotlight) | |
| Zero-Shot Uncertainty-Aware Deployment of Simulation Trained Policies on Real-World Robots (Poster) | |
| Tutorial: Safe Learning for Decision Making (Tutorial) | |
| Reward-Based Environment States for Robot Manipulation Policy Learning (Poster) | |