In-Hand Robotic Manipulation Under Contact and Friction Uncertainty
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Robotic systems face challenges in performing complex manipulation tasks due to uncertainty in parameters like friction coefficient and grasping location, leading to failures during contact-rich maneuvers, especially with simple parallel-jaw grippers.
Innovation Solution
A robust manipulation framework that uses a gripper with actuators to maintain external contacts, incorporating uncertainty estimates in planning and control, computing a motion cone to minimize in-hand translation and prevent slip, using in-gripper mechanics models and sensing modalities like vision and touch.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a simple parallel-jaw gripper is used to grasp objects, then the device complexity is reduced, but the ability to perform complex manipulation tasks deteriorates due to limited dexterity
Solution Approach 1:
The patent introduces environmental contacts as intermediaries between the simple gripper and the manipulation task. By making the object contact with environmental surfaces (walls, floors, ceilings), the system compensates for the gripper's limited dexterity. The environmental contacts act as additional interaction points that enable complex manipulation behaviors despite using a simple parallel-jaw gripper.
2Adaptability or versatility
If contact-rich manipulation maneuvers are performed, then the adaptability to achieve complex tasks is improved, but the reliability deteriorates due to uncertainty in friction coefficient and grasping location
Solution Approach 1:
The patent applies preliminary action by planning multiple contact formations in advance and preparing contingency plans for different contact scenarios. The system pre-computes manipulation sequences that account for potential uncertainties in friction and grasping location, allowing it to adapt during execution without failing. This includes planning alternative contact points and adjustment maneuvers before uncertainties manifest.
Solution Approach 2:
The patent implements dynamics by making the manipulation plan adaptive and adjustable during execution. The system continuously monitors contact status and adjusts gripper forces, velocities, and contact points in real-time based on actual friction conditions and object pose. This dynamic adjustment capability allows the system to maintain reliability despite initial uncertainties in contact parameters.
3Adaptability or versatility
If multiple contact formations are used during manipulation, then the adaptability to perform complex tasks is improved, but the difficulty of controlling contact modes increases due to parametric uncertainty
Solution Approach 1:
The patent implements feedback mechanisms to continuously monitor contact parameters such as contact forces, friction conditions, and object pose during manipulation. This feedback information is used to adjust gripper actions and maintain desired contact modes despite parametric uncertainties. The system measures actual contact conditions and uses this information to correct deviations from planned contact formations.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Ensures successful reorientation of objects by maintaining contact with the environment, reducing slip, and adapting to parametric uncertainties, thereby enhancing robotic dexterity and reliability in real-world tasks.
Implementation Method 1
the uncertainty in the involved parameters like the coefficient of friction
Data Source
AI summary
A controller is provided for manipulating an object having at least one external contact by using a gripper of a robot arm having actuators. The controller includes a signal interface configured to receive a contact signal from the gripper and transmit a control signal to the actuators, a memory configured to store computer-implemented programs including an in-gripper mechanics model and a robust tuning framework, a processor configured to perform instructions of the computer programs. The instructions include steps of computing an object in-hand slippery of the gripper for the object based on the contact signal, computing a naive motion cone that maintains a desired contact mode assuming contact parameters between the object and the gripper, refining the naive motion cone based on an uncertainty range of each of the contact parameters, generating a manipulator position trajectory that minimizes the in-gripper slippery from the refined motion cone, and controlling the gripper according to the generated manipulator position trajectory by transmitting a gripper trajectory position signal to the actuators of the robot arm to reorient the object in the gripper using at least one external contact.