Traffic-Aware Mobile Robot Path Planning With Future Occupancy Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In facilities with multiple autonomous or semi-autonomous mobile robots, path planning algorithms often fail to account for future occupancy, leading to potential collisions and congestion as robots may plan to traverse the same region at the same time, resulting in inefficient navigation and triggering of collision-avoidance mechanisms.
Innovation Solution
The implementation of a decentralized traffic-aware navigational planning method that uses occupancy maps to generate paths based on both current and future occupancies of facility regions, allowing robots to detect obstacles and transmit occupancy data for updating maps, thereby avoiding congestion by considering future positions of other robots.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If separate robots generate paths independently without considering future occupancy, then each robot can plan its path quickly and simply, but paths may conflict leading to collisions and congestion
Solution Approach 1:
The system performs preliminary actions by predicting future occupancy of facility regions before generating paths. Robots use occupancy maps that incorporate predicted future positions of other robots to proactively avoid potential conflicts, rather than reacting to collisions after they occur. This preliminary planning based on forecasted states resolves the contradiction by enabling reliable collision avoidance while maintaining relatively simple individual robot path generation.
Solution Approach 2:
The system implements feedback mechanisms where robots transmit occupancy data about their current and future positions to a central system or other robots. This feedback loop allows the occupancy map to be continuously updated with actual and predicted robot positions, enabling dynamic path adjustment. The feedback principle resolves the contradiction by providing the necessary information for reliable collision avoidance without requiring each robot to independently perform complex global path planning.
2Productivity
If multiple robots traverse the same facility regions simultaneously without coordination, then navigation speed is maintained, but congestion occurs reducing overall efficiency
Solution Approach 1:
The system applies preliminary action by predicting future occupancy of facility regions and using these predictions to generate conflict-free paths. Before robots actually traverse regions, the system forecasts which regions will be occupied and routes robots accordingly, preventing congestion before it occurs. This approach maintains navigation speed while avoiding congestion delays by proactively coordinating robot movements through future occupancy prediction.
3Reliability
If a centralized system coordinates all robot paths to avoid conflicts, then collision avoidance is improved, but computational burden on central server increases
Solution Approach 1:
The system applies segmentation by dividing the path planning task between individual robots and a central coordination system. Each robot independently generates its own path based on occupancy maps, while the central system coordinates by collecting occupancy data and updating the global occupancy map. This segmentation reduces the computational burden on the central server compared to centralized path generation, while still maintaining reliable collision avoidance through coordinated occupancy awareness.
Solution Approach 2:
The system implements self-service by enabling each robot to generate its own path using occupancy map data. Instead of the central server computing paths for all robots, each robot autonomously plans its path based on the shared occupancy information. This self-service approach significantly reduces computational energy requirements while maintaining collision avoidance through the shared occupancy awareness provided by the coordination system.
Data Source
AI summary
A method includes: storing an occupancy map for a facility, the occupancy map defining: for each of a plurality of regions in the facility, a current occupancy for a present time value, and for each of at least a subset of the regions, a future occupancy for a subsequent time value; generating a path from a current pose of a mobile robot in the facility to a target pose, based on the current and future occupancies; in response to execution of the path at the mobile robot, capturing sensor data representing a vicinity of the mobile robot; detecting an obstacle from the sensor data; and transmitting occupancy data for generating an updated occupancy map including an updated future occupancy for at least one of the subset of regions, the occupancy data including obstacle data indicating a location of the obstacle, and path data defining the path.