Grasp Planning For Digital Human Models Using Oriented Bounding Boxes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current digital human modeling systems lack an efficient method to automatically determine grasping parameters for unknown objects, particularly in manufacturing contexts, often resulting in unrealistic final postures due to the lack of consideration for the digital human model's posture during grasping.
Innovation Solution
A grasp planner is developed that determines the optimal grasp location, orientation, and type for unknown objects by using an oriented bounding box, inverse kinematic solver, and grasping hierarchy, accounting for the digital human model's posture, and is integrated into existing frameworks like the Smart Posture Engine to simulate plausible interactions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If automatic grasp determination is implemented without considering DHM posture, then automation is improved, but realism of final posture deteriorates
Solution Approach 1:
The system performs preliminary posture analysis before determining the final grasp configuration. The DHM posture is evaluated in advance to identify feasible grasping positions, ensuring that the automatic grasp determination process selects only those grasps that result in realistic and ergonomic final postures.
Solution Approach 2:
The system incorporates feedback loops where the determined grasp configuration is evaluated against DHM posture constraints. If the initial automatic grasp determination produces unrealistic postures, the system adjusts the grasp parameters based on posture feedback until a realistic configuration is achieved.
2Reliability
If grasp parameters are manually specified for each object, then posture realism is improved, but productivity deteriorates
Solution Approach 1:
The system enables self-service automatic grasp determination where the DHM automatically determines appropriate grasp parameters for unknown objects based on its own posture capabilities and the object's geometry, eliminating the need for manual specification while maintaining posture realism.
Solution Approach 2:
The system dynamically adjusts grasp parameters such as contact points, force directions, and gripper orientation based on the DHM's current posture and the object's characteristics, allowing automatic adaptation that maintains realism without manual intervention.
3Device complexity
If simple bounding box methods are used for grasp planning, then device complexity is reduced, but measurement precision deteriorates
Solution Approach 1:
The system segments the object surface into multiple candidate regions based on geometric features and curvature analysis. Instead of using a single simple bounding box, the method divides the object into graspable zones, allowing more precise determination of optimal contact points while keeping the overall algorithm relatively simple.
Solution Approach 2:
The system transitions from two-dimensional bounding box projections to three-dimensional surface analysis by examining object curvature, normal vectors, and surface geometry in 3D space. This dimensional enhancement improves grasp location precision without requiring overly complex algorithms.
Data Source
AI summary
An embodiment receives models of an object and an environment and an indication of position of a digital human model (DHM). An oriented bounding box (with a plurality of faces) surrounding the model of the object is determined and, for each of the plurality of faces, a candidate grasp location, a candidate grasp orientation, and a candidate grasp type is determined. From amongst the plurality of faces, one or more graspable faces is determined based on: the candidate grasp locations, the candidate grasp orientations, the environment model, and dimensions of each face. Then, an optimal graspable face is identified based on a hierarchy and the position of the DHM. An inverse kinematic solver determines position and orientation, i.e., grasp, of an end effector of the DHM grasping the object based on the candidate grasp location, candidate grasp orientation, and candidate grasp type of the optimal graspable face.