There is a rapidly growing interest in the research and development of perception and manipulation algorithms to support robotic warehouse automation. In the past, many robotic manipulation systems have been isolated to highly structured environments. Current research trends to improve perception algorithms along with innovation in manipulator design have started to bridge the gap towards solving a wide variety of manipulation challenges in semi and unstructured environments.
This workshop provides a venue for computer vision, robotics and AI researchers from industry and academia to discuss and exchange ideas along the areas of perception algorithms, gripper technologies, planning in constrained spaces, deformable object handling and learned grasping policies. During the workshop, we aim to explore:
- What datasets currently exist, what are the limitations and what kinds of data should be explored,
- Various approaches to solving the perception challenges for cluttered environments including visual identification, 3D scene reconstruction and pose estimation,
- Manipulator and gripper designs along with grasp planning and affordance algorithms that can unlock the ability to reliably manipulate millions of objects with varying geometric and physical properties, and
- Discussions around future problems that still remain and possible approaches to solve those problems.
Call for Papers
Participants are encouraged to submit their research for presentation at the workshop. The submitted papers should be no more than 4 pages (excluding references and appendix) and should follow the RSS paper format. Submitted papers will be reviewed by the organizing committee. Accepted papers will be hosted on the workshop website and presented in poster and spotlight sessions. Topics of interest include but are not limited to:
- Representations and state estimation for robotic manipulation.
- Datasets and benchmarking.
- Perception for grasping and manipulation.
- End-effector design.
- Planning and control in constrained spaces.
- Reinforcement learning at scale.
- Role of simulation in warehouse manipulation and bridging the Sim2Real gap.
- Submission Deadline: June 4, 2023
- Author Notification: June 15, 2023
- Camera Ready Submission: June 25, 2023
- Workshop: July 10, 2023
Submission Website: https://cmt3.research.microsoft.com/warehousemanipulation2023/
July 10, 2023 - Korean Standard Time (GMT+9)
- 09.00-09.10: Welcome and Introduction
- 09.10-09.30: "ARMBench: An Object-centric Benchmark Dataset for Robotic Manipulation"
Chaitanya Mitash and Manikantan Nambi
- 09.30-09.50: "Robotic Stow to Fabric Pod with Compliant Manipulation"
- 09.50-10.10: "Multi-Modalities in Robotic Manipulation"
- 10.10-10.30: "Demonstrating Large-Scale Package Manipulation via Learned Metrics of Pick Success"
- 10.30-11.00: Coffee Break
- 11.00-11.30: "Practical Robotic Scene Awareness"
- 11.30-12.00: "Leveraging Symmetries in Robotic Learning"
- 12.00-13.30: Lunch
- 13.30-14:00: "Tactile Perception for Dexterous Manipulation"
- 14.00-14.30: "Robot Manipulation with Human-level Dexterity"
- 14.30-15.00: Spotlight Session
"Towards robustly picking unseen objects from densely packed shelves"
Markus Grotz, Soofiyan Atar, Yi Li, Paolo Torrado, Boling Yang, Nick Walker, Michael Murray, Maya Cakmak and Joshua Smith
"A versatile robotic hand with 3D perception, force sensing for autonomous manipulation"
Nikolaus Correll, Dylan Kriegman, Stephen Otto and James Watson
"DoUnseen: Tuning-Free Class-Adaptive Object Detection of Unseen Objects for Robotic Grasping"
Anas Gouda and Moritz Roidl
"Learning-Free Grasping of Unknown Objects Using Hidden Superquadrics"
Yuwei Wu, Weixiao Liu, Zhiyang Liu and Gregory S. Chirikjian
- 15.00-15.30: Coffee Break and Poster Session
- 15.30-16.00: "High performance and reliability in robot manipulation for logistics"
Felix von Drigalski
- 16.00-16.30: "Getting a grasp on food supply: Challenges in fresh produce packing"
- 16.30-17.00: QA + Panel Discussion
For further information please reach out to us at email@example.com