Bridging Sensing, Planning and Interaction
Bridging Sensing, Planning and Interaction
Active perception plays a central role in robotics, enabling systems to intelligently acquire informative data by optimizing their sensing and interaction strategies. This workshop focuses on the intersection of perception, planning, and interaction, addressing key challenges in vision-based navigation and manipulation.
Topics of interest include data-driven perception, reinforcement learning for active vision, multi-robot exploration, and perception through interaction—encompassing understanding, reasoning, and decision-making. The event aims to bridge the gap between planning-centric robotics and perception-driven methodologies.
Robot arms and hands adjust their pose, force, or tactile sensing to better understand objects before grasping them.
Robots actively plan their viewpoints to improve Simultaneous Localization and Mapping (SLAM) efficiency and accuracy.
Robots actively plan their viewpoints to improve Simultaneous Localization and Mapping (SLAM) efficiency and accuracy.
Actively combining information from RGB, LiDAR, radar, thermal, event cameras (...) to improve perception.
Deciding where to move sensors next for better perception in tasks like localization, mapping, or object search.
Robots actively gather missing or uncertain information to improve their models and make better decisions.
Poster Presentation and Highlight Talks
Speakers from Diverse Application Areas
| 08:25 – 08:35 | Welcome Remarks Organizing Committee |
| 08:35 – 09:00 | Sebastian Scherrer (CMU) – remote Plenary Talk: Multi-Robot Information Gathering in Challenging Environments |
| 09:00 – 09:25 | Tai Wang (Shanghai AI Lab) Plenary Talk: Towards a Vision-Language Navigation Foundation Model via Sim2Real |
| 09:25 – 09:50 | Marija Popovic (TU Delft) Plenary Talk: Reinforcement Learning for Active Perception using UAVs |
| 09:50 – 10:10 | Spotlight Talks Presentations from selected award finalists |
| 10:10 – 10:50 | Coffee Break ☕ Poster Session |
| 10:50 – 11:15 | Boyu Zhou (SUSTech) Plenary Talk: Autonomous Exploration: From Traditional to AI-driven Approaches |
| 11:15 – 11:40 | Jianxiang Feng (Agile Robots) Plenary Talk: Learning Robust Perception and Manipulation via Uncertainty-Aware Intelligence |
| 11:40 – 12:05 | Stefan Leutenegger (ETH Zurich) Plenary Talk: Exploration with Drones for Geometric and Semantic Reconstruction in the Wild |
| 12:05 – 12:30 | Interactive Discussion Guided group discussions including invited speakers and organizers on “What’s Next in Active Perception” |
| 12:30 – 12:45 | Award & Closing Remarks Final remark by organization committe and award presentation |
You are provided with a sparse map of the environment and assume to have a robot equipped with a camera that can freely rotate with respect to the mobile base. Given some robot waypoints, the goal is to rotate the camera towards more meaningful parts of the map, improving localization accuracy.
