Robot Route Switching Based on Perception Uncertainty
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomy systems for robots are limited in extensibility and efficiency, typically focusing on a narrow mission set, which hinders their adaptability and operational flexibility.
Innovation Solution
A system and method for robots that dynamically transition between global and local routes based on perception uncertainty, using a configuration space to manage robot states and environments, enabling conflict detection and avoidance through a mission management system (MMS) with adaptable autonomy architecture.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If existing autonomy systems focus on a narrow mission set, then the design of underlying autonomy algorithms and software architecture can be simplified, but the extensibility and adaptability of the system deteriorates
Solution Approach 1:
The patent implements a universal autonomy system architecture that can handle multiple mission types (aerial, ground, maritime, space) through a common framework. The system uses configurable mission parameters and adaptable algorithms that can be adjusted for different robot types and mission requirements, allowing one system to perform multiple functions without requiring separate specialized systems for each mission type.
2Reliability
If the robot transitions to local route when perception uncertainty exceeds threshold, then conflict detection and avoidance capability is improved, but deviation from global route and mission time may increase
Solution Approach 1:
The system continuously monitors perception uncertainty levels and uses this feedback to dynamically adjust routing decisions. When uncertainty exceeds a threshold, the system transitions to local route planning; when uncertainty decreases below the threshold, it returns to the global route. This closed-loop feedback mechanism ensures reliable conflict detection while minimizing unnecessary deviations from the optimal global path.
Data Source
Figure 1
Figure 2~3
Figure 4~5
AI summary
A method is provided for detecting and avoiding conflict during a mission of a robot that includes a global route of travel. The method includes monitoring a state of the robot and a state of an environment of the robot as the robot travels the global route. The method includes generating a local route of travel through a region of the environment that includes the robot, the region having a size and shape that are set based on a type of the robot and the state of the robot when the local route is generated. A measure of uncertainty in the perception of objects in the region is monitored based on the state of the environment. And the robot is caused to maintain the global route or transition to the local route based on a comparison of the measure of uncertainty and an uncertainty threshold.