Sequential Manipulation

Sequential manipulation research focuses on enabling robots and AI systems to perform complex tasks involving a series of coordinated actions, often requiring interaction with multiple objects and environments. Current efforts concentrate on improving planning algorithms, particularly those integrating multimodal data (visual, tactile, force) with large language models or leveraging model predictive control and reinforcement learning techniques to handle uncertainty and sparse rewards. This field is crucial for advancing robotics capabilities in areas like manufacturing, healthcare, and daily assistance, driving progress in both efficient task planning and robust execution in dynamic, real-world settings.

Papers

August 1, 2022

Relay Hindsight Experience Replay: Self-Guided Continual Reinforcement Learning for Sequential Object Manipulation Tasks with Sparse Rewards
Yongle Luo, Yuxin Wang, Kun Dong, Qiang Zhang, Erkang Cheng, Zhiyong Sun, Bo Song
Reinforcement Learning Sparse Reward Continual Reinforcement Learning Guided Exploration Sequential Manipulation Hindsight Experience Replay Unsupervised Exploration

May 26, 2022

Reinforcement Learning Approach for Mapping Applications to Dataflow-Based Coarse-Grained Reconfigurable Array
Andre Xian Ming Chang, Parth Khopkar, Bashar Romanous, Abhishek Chaurasia, Patrick Estep, Skyler Windh, Doug Vanesko, Sheik Dawood Beer Mohideen, Eugenio Culurciello
Proximal Policy Optimization Reinforcement Learning Approach Sequential Manipulation Streaming Capable High Performance Architecture Coarse Grained Reconfigurable Array

March 10, 2022

Sequence-of-Constraints MPC: Reactive Timing-Optimal Control of Sequential Manipulation
Marc Toussaint, Jason Harris, Jung-Su Ha, Danny Driess, Wolfgang Hönig
Motion Planning Model Predictive Control Waypoint Generation Sequential Manipulation Reactive Behavior Time Optimal Control

March 8, 2022

Learning Sensorimotor Primitives of Sequential Manipulation Tasks from Visual Demonstrations
Junchi Liang, Bowen Wen, Kostas Bekris, Abdeslam Boularias
Manipulation Task Video Demonstration Motion Primitive Task Demonstration Sequential Manipulation Complex Robotic Task

Sequential Manipulation

Papers

Relay Hindsight Experience Replay: Self-Guided Continual Reinforcement Learning for Sequential Object Manipulation Tasks with Sparse Rewards

Reinforcement Learning Approach for Mapping Applications to Dataflow-Based Coarse-Grained Reconfigurable Array

Sequence-of-Constraints MPC: Reactive Timing-Optimal Control of Sequential Manipulation

Learning Sensorimotor Primitives of Sequential Manipulation Tasks from Visual Demonstrations