On-Board Robot Mapping for Dynamic Routing in Unknown Spaces
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous robots face challenges in navigating through complex, unknown environments due to the lack of efficient algorithms that integrate mapping and routing, particularly in situations where direct paths are blocked or when exploring unmapped areas, and existing solutions fail to consider operational constraints like battery limitations and navigation safety.
Innovation Solution
The implementation of exploratory on-board mapping methods that generate topological maps using depth images from depth cameras, allowing robots to dynamically route themselves by identifying free spaces, translating paths into candidate locations, and using a dynamic filter to maintain bounded error and avoid collisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the robot uses simple reactive navigation based on sensor information, then the robot can navigate in unknown environments, but the robot cannot maintain a sufficiently accurate and compact map representation to adapt motion and avoid collisions
Solution Approach 1:
The patent combines mapping and routing functions into a unified system. The reactive mapper continuously builds and updates a compact topological map while the router uses this map for path planning. This merging allows the robot to maintain accurate environmental representation and adapt its motion to avoid collisions simultaneously.
Solution Approach 2:
The system implements continuous feedback through the reactive mapper that processes sensor information and updates the map representation in real-time. This feedback loop enables the robot to adapt its routing based on the current map state and sensor readings, ensuring navigation safety while maintaining accurate environmental awareness.
2Reliability
If the robot maintains a detailed map of the environment, then the robot can adapt its motion to avoid collisions, but the processing requirements and computational load increase
Solution Approach 1:
The patent segments the environment representation into discrete topological elements (nodes and edges) rather than maintaining continuous detailed maps. This segmentation creates a compact map structure that reduces processing requirements while preserving essential spatial information needed for collision avoidance and path planning.
Solution Approach 2:
The system changes the parameter representation of the environment from detailed geometric descriptions to topological relationships. This parameter transformation reduces computational complexity while maintaining the information necessary for navigation and collision avoidance decisions.
3Productivity
If the robot follows a direct path to the target location, then the navigation is efficient, but the robot cannot handle blocked paths or explore unmapped areas
Solution Approach 1:
The routing system is implemented as a dynamic process that continuously evaluates the current map state and sensor information. When obstacles are detected or the environment changes, the router dynamically recalculates paths using the updated topological map, allowing the robot to adapt to blocked paths while maintaining navigation efficiency through real-time replanning.
4Adaptability or versatility
If the robot explores unknown environments reactively, then the robot can navigate without pre-mapping, but the robot cannot efficiently exploit promising directions while storing alternative paths for backtracking
Solution Approach 1:
The reactive mapper continuously builds and maintains a topological map during exploration, performing preliminary mapping actions as the robot moves through unknown environments. This preliminary action enables efficient path planning and backtracking decisions without requiring complete pre-mapping, reducing navigation time while maintaining exploration capability.
Data Source
AI summary
Methods and apparatus for dynamically routing robots based on exploratory on-board mapping are disclosed. A control system of a robot includes an image manager to command a depth camera to capture depth images of an environment. The depth camera has a field of view. The control system further includes a map generator to generate a map of the environment based on the depth images. The map includes a representation of unoccupied space within the environment, and a path extending through the unoccupied space from a reference location of the robot to a target location of the robot. The control system further includes a field of view evaluator to determine whether the field of view associated with the reference location satisfies a threshold. The control system further includes a route generator to generate, in response to the field of view associated with the reference location satisfying the threshold, a route to be followed by the robot within the environment. The route includes a first candidate location located along the path of the map between the reference location and the target location. The first candidate location is within the field of view associated with the reference location.