Autonomous Mobile Device Predictive Obstacle Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional collision avoidance techniques for autonomous mobile robots struggle to predict human movement accurately, leading to difficulties in taking safe, easy, and smooth evasive actions when encountering moving persons.
Innovation Solution
An autonomous mobile device equipped with a control device that includes a first sensing unit for obstacle detection, a storage unit for storing temporal positional fluctuation information, and a region setting unit to set a virtual obstacle region based on predicted movement, allowing the device to anticipate and avoid collisions with moving persons.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If linear prediction based on velocity vector is used, then the robot can avoid collision with moving persons, but it is difficult to predict actual movement and take safe evasive action
Solution Approach 1:
The patent applies preliminary action by predicting multiple potential future positions of the moving person ahead of time and creating virtual obstacle regions at these predicted locations. Instead of waiting for the person to actually move, the system proactively prepares avoidance paths by anticipating where the person might go, allowing the robot to plan safe evasive actions in advance.
Solution Approach 2:
The patent implements dynamics by transitioning from static linear velocity vector prediction to dynamic prediction that incorporates temporal positional fluctuation. The system now considers multiple possible trajectories and creates time-varying virtual obstacle regions that adapt to the uncertain future movements of the person, making the prediction model more dynamic and realistic.
2Ease of operation
If the robot takes evasive action based on linear velocity prediction, then collision avoidance is attempted, but the evasive action may be unsafe due to unforeseeable movement
Solution Approach 1:
By predicting multiple future positions and creating virtual obstacle regions in advance, the system prepares multiple safe avoidance paths before the person actually moves. This preliminary planning ensures that when evasive action is needed, the robot already has pre-computed safe paths to follow, making the action both smooth and reliable.
Solution Approach 2:
The system uses feedback by continuously monitoring the actual position of the moving person and comparing it with predicted positions. The virtual obstacle regions are updated based on the person's actual movement pattern, allowing the system to adjust and refine its predictions, thereby improving the safety and smoothness of evasive actions over time.
Data Source
AI summary
An autonomous mobile device has its movement controlled by a control device and includes a first sensing unit for sensing an obstacle. The control device includes a first storage unit for storing information as to a temporary positional fluctuation of the obstacle and sets as a virtual obstacle region a region where it is predicted that the obstacle sensed by the first sensing unit travels following a predetermined time passage based on the information as to the temporary positional fluctuation of the obstacle stored in the first storage unit.