Bilateral Control

Bilateral control, a robotics and autonomous systems control strategy, focuses on improving system performance by incorporating feedback from both the controlled system and its environment. Current research emphasizes using machine learning, particularly transformer-based models and deep reinforcement learning, to enhance the adaptability and precision of bilateral control in applications like robotic manipulation and autonomous driving. This approach shows promise in achieving superior performance compared to unilateral control methods, as demonstrated by improved stability, responsiveness, and efficiency in various tasks, potentially leading to advancements in both robotics and intelligent transportation systems.

Papers

January 31, 2024

Bi-ACT: Bilateral Control-Based Imitation Learning via Action Chunking with Transformer
Thanpimon Buamanee, Masato Kobayashi, Yuki Uranishi, Haruo Takemura
Transformer Based Robot Control Robot Arm Action Chunking Autonomous Manipulation Bilateral Control

January 30, 2024

ILBiT: Imitation Learning for Robot Using Position and Torque Information based on Bilateral Control with Transformer
Masato Kobayashi, Thanpimon Buamanee, Yuki Uranishi, Haruo Takemura
Transformer Based Robot Person Imitation Learning Long Short Term Memory Robot Arm Autonomous Manipulation Distance Dependent Torque Bilateral Control

March 3, 2022

Bilateral Deep Reinforcement Learning Approach for Better-than-human Car Following Model
Tianyu Shi, Yifei Ai, Omar ElSamadisy, Baher Abdulhai
Reinforcement Learning Autonomous Driving Autonomous Vehicle Full Model Car Following Bilateral Network Bilateral Control

Bilateral Control

Papers

Bi-ACT: Bilateral Control-Based Imitation Learning via Action Chunking with Transformer

ILBiT: Imitation Learning for Robot Using Position and Torque Information based on Bilateral Control with Transformer

Bilateral Deep Reinforcement Learning Approach for Better-than-human Car Following Model