A Closed-Chain Approach to Generating Affordance Joint Trajectories for Robotic Manipulators
Janak Panthi, Farshid Alambeigi, Mitchell Pryor
AI summary
Problem
Prior screw-based affordance frameworks struggle with singularity navigation, undesirable configuration avoidance, task success prediction, and lack independent control over gripper orientation along the manipulation path.
Approach
The method models the robot and task affordance as a unified closed-chain mechanism, leveraging screw theory and a novel inverse kinematics solver to compute complete joint trajectories in real time while accommodating user-defined gripper orientation constraints.
Key results
- Rapid real-time trajectory generation (0.0077–0.098 s)
- 4x faster planning time compared to state-of-the-art methods
- Reduced joint movement with higher task success rates
- Validated on UR5 simulation and Boston Dynamics Spot hardware
Why it matters
Provides a versatile, training-free framework that allows robots to safely and efficiently execute diverse constrained manipulation tasks in unpredictable real-world environments.
Abstract
Robots operating in unpredictable environments re- quireversatile,hardware-agnosticframeworkscapableofadapting to various tasks. While a recent screw-based affordance approach shows promise, it faces challenges in avoiding undesirable con- figurations, singularity navigation, and task success prediction. To address these limitations, we propose a novel framework that incorporates gripper orientation control and generates complete joint trajectories in real time for screw-based task affordance execution. Our method models the affordance and manipulator as a closed-chain mechanism, introducing an innovative approach to solving closed-chain inverse kinematics. It encapsulates task con- straints and simplifies task definitions, while remaining hardware and robot agnostic, robust to errors, and invariant to the initial grasp. We validate our framework with simulations on a UR5 robot and real-world implementation on a Boston Dynamics Spot robot. Our experiments demonstrate rapid joint trajectory generation (0.0077–0.098 s) for various tasks, including a 420◦valve turn with consideration of the gripper orientation. Comparison with the state-of-the-art methods shows a 4x improvement in planning time, reduced joint movement, and achievement of greater task goals. Video demonstrations and the open-source code for this project are available online.