Robot Base Position Planning for Collision-Free Manipulator Reach
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional robotic systems face inefficiencies in determining collision-free trajectories for interacting with objects in dynamic environments, as they rely on computationally expensive guess-and-check methods, leading to slowed operations and hesitant behavior.
Innovation Solution
A pre-trained machine learning model, such as an artificial neural network, is used to predict candidate positions for a robotic device's base, allowing the manipulator to reach interaction points without collisions, by processing height maps of the environment and selecting positions with high confidence levels for collision-free trajectory planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional guess-and-check methods are used to determine collision-free trajectories, then the robotic system can ensure safety by validating each candidate position, but the operation speed decreases and the system exhibits hesitant behavior
Solution Approach 1:
The system performs preliminary action by using a pre-trained machine learning model to predict candidate base positions that are likely to enable collision-free trajectories. This preliminary prediction filters out invalid positions before the expensive guess-and-check validation process, allowing the system to maintain reliability while operating faster by focusing computational resources on promising candidates rather than exhaustively checking all possible positions
2Reliability
If conventional guess-and-check methods are used to determine base positions, then the system can find valid positions, but the time required increases significantly
Solution Approach 1:
The system replaces the mechanical guess-and-check method with a machine learning-based prediction system. The pre-trained model substitutes for the iterative trial-and-error process by directly predicting candidate positions that are likely to be valid, dramatically reducing the time required to determine suitable base positions while maintaining the reliability of collision-free trajectory validation
Solution Approach 2:
The machine learning model performs preliminary identification of candidate positions before the validation step, preparing a filtered set of promising candidates. This preliminary action eliminates the need to randomly sample and validate numerous invalid positions, thereby reducing the time loss while preserving the reliability guarantee of validating actual candidates
Data Source
AI summary
A method includes receiving sensor data representative of surfaces in a physical environment containing an interaction point for a robotic device, and determining, based on the sensor data, a height map of the surfaces in the physical environment. The method also includes determining, by inputting the height map and the interaction point into a pre-trained model, one or more candidate positions for a base of the robotic device to allow a manipulator of the robotic device to reach the interaction point. The method additionally includes determining a collision-free trajectory to be followed by the manipulator to reach the interaction point when the base of the robotic device is positioned at a selected candidate position of the one or more candidate positions and, based on determining the collision-free trajectory, causing the base of the robotic device to move to the selected candidate position within the physical environment.