Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Task and Joint Space Dual-Arm Compliant Control

Alexander L. Mitchell, Tobit Flatscher, Ingmar Posner

TL;DR

The paper addresses safe, compliant manipulation with friction-prone rigid robots by introducing a real-time open-source impedance controller that seamlessly blends joint-space and task-space compliance. It formulates a composite torque objective with a model-free friction observer, enabling smooth transitions between compliance modes and robust end-effector tracking. The approach is implemented on the dual-arm Frank platform with Kinova Gen3 arms, integrated with ROS tools, and supports high-frequency trajectory streaming for learning-based, planning-based, or teleoperation workflows. The results demonstrate precise pin-insertion capability and strong safety by maintaining task performance under external disturbances, underscoring the practical impact for delicate manipulation and human-robot interaction.

Abstract

Robots that interact with humans or perform delicate manipulation tasks must exhibit compliance. However, most commercial manipulators are rigid and suffer from significant friction, limiting end-effector tracking accuracy in torque-controlled modes. To address this, we present a real-time, open-source impedance controller that smoothly interpolates between joint-space and task-space compliance. This hybrid approach ensures safe interaction and precise task execution, such as sub-centimetre pin insertions. We deploy our controller on Frank, a dual-arm platform with two Kinova Gen3 arms, and compensate for modelled friction dynamics using a model-free observer. The system is real-time capable and integrates with standard ROS tools like MoveIt!. It also supports high-frequency trajectory streaming, enabling closed-loop execution of trajectories generated by learning-based methods, optimal control, or teleoperation. Our results demonstrate robust tracking and compliant behaviour even under high-friction conditions. The complete system is available open-source at https://github.com/applied-ai-lab/compliant_controllers.

Task and Joint Space Dual-Arm Compliant Control

TL;DR

The paper addresses safe, compliant manipulation with friction-prone rigid robots by introducing a real-time open-source impedance controller that seamlessly blends joint-space and task-space compliance. It formulates a composite torque objective with a model-free friction observer, enabling smooth transitions between compliance modes and robust end-effector tracking. The approach is implemented on the dual-arm Frank platform with Kinova Gen3 arms, integrated with ROS tools, and supports high-frequency trajectory streaming for learning-based, planning-based, or teleoperation workflows. The results demonstrate precise pin-insertion capability and strong safety by maintaining task performance under external disturbances, underscoring the practical impact for delicate manipulation and human-robot interaction.

Abstract

Robots that interact with humans or perform delicate manipulation tasks must exhibit compliance. However, most commercial manipulators are rigid and suffer from significant friction, limiting end-effector tracking accuracy in torque-controlled modes. To address this, we present a real-time, open-source impedance controller that smoothly interpolates between joint-space and task-space compliance. This hybrid approach ensures safe interaction and precise task execution, such as sub-centimetre pin insertions. We deploy our controller on Frank, a dual-arm platform with two Kinova Gen3 arms, and compensate for modelled friction dynamics using a model-free observer. The system is real-time capable and integrates with standard ROS tools like MoveIt!. It also supports high-frequency trajectory streaming, enabling closed-loop execution of trajectories generated by learning-based methods, optimal control, or teleoperation. Our results demonstrate robust tracking and compliant behaviour even under high-friction conditions. The complete system is available open-source at https://github.com/applied-ai-lab/compliant_controllers.
Paper Structure (8 sections, 6 equations, 3 figures, 1 table)

This paper contains 8 sections, 6 equations, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Impedance Formulation
  3. Sending Setpoints To The Controller
  4. Dynamic Reconfigure for Different Controller Behaviours
  5. Results
  6. Controller Evaluation
  7. Qualitative Results
  8. Conclusions

Figures (3)

  • Figure 1: Task- and joint-space compliant control as deployed on our real dual-arm platform christened Frank. The controller is based on compliant_formulation. We combine the joint- and task-space formulations to create a tracking controller precise enough to perform pin insertions, whilst remaining compliant and safe for human-robot interaction. Please find and use our implementation at https://github.com/applied-ai-lab/compliant_controllers.
  • Figure 2: The dual-arm robot performing a precise pin insertion task during a RAMP collins2023ramp small-batch manufacturing task. The end-effector forces are measured by projecting the joint torques into the end-effector frame. Complete videos are found https://github.com/applied-ai-lab/compliant_controllers.
  • Figure 3: The controller is compliant, meaning that it is safe for humans to intervene during operation. Here, a bystander applies a force of up to 30N to the left robot arm. Simultaneously, the right arm reacts to this disturbance and tracks the disturbance.