AMR Path Planning With Weighted Targets for SLAM Map Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous mobile robots (AMRs) face challenges in accurately mapping and localizing within unknown or changing environments due to imperfect sensor data, leading to corrupted map data, inefficient routes, and potential collisions, as conventional SLAM algorithms struggle with error accumulation and phantom objects.
Innovation Solution
The navigation and localization system employs improved SLAM algorithms with features like target/path selection based on weighting functions, error vector checking, and feed-forward combiners to enhance mapping accuracy, reduce errors, and prevent collisions by prioritizing targets and correcting positional estimates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If SLAM algorithms are used for mapping and localization in unknown environments, then the robot can navigate autonomously, but sensor errors cause map corruption and localization inaccuracies
Solution Approach 1:
The system implements feedback by continuously comparing sensor observations with the current map model, detecting inconsistencies and errors. When discrepancies are found between expected and actual sensor data, the system adjusts the map and localization estimates to correct accumulated errors, creating a closed-loop control system that maintains reliability during autonomous operation
Solution Approach 2:
The system performs preliminary actions by proactively detecting error patterns in sensor data before they significantly corrupt the map. Error detection mechanisms identify problematic sensor readings early, allowing the system to correct localization drift and map inaccuracies before they accumulate to dangerous levels that would compromise navigation safety
2Productivity
If the robot moves quickly through the environment, then productivity increases, but localization errors accumulate faster causing collisions and inefficient routes
Solution Approach 1:
The system applies dynamics by continuously adapting the localization algorithm parameters based on the robot's current speed and motion state. When moving faster, the system increases the frequency of localization corrections and adjusts the weighting of different sensor inputs to compensate for increased error accumulation, allowing high-speed navigation while maintaining position accuracy
Solution Approach 2:
The system changes parameters dynamically by adjusting the time between localization updates and the confidence weights assigned to sensor data based on the robot's velocity. At higher speeds, the system reduces the time between corrections and increases reliance on relative positioning methods, enabling maintained precision despite increased productivity demands
3Reliability
If frequent sensor scans are performed to maintain accurate mapping, then map accuracy improves, but the robot moves more slowly and takes inefficient routes
Solution Approach 1:
The system applies partial action by performing sensor scans at selectively optimized intervals rather than continuously. The error detection system identifies when sufficient data has been collected to maintain map accuracy without requiring constant scanning, allowing the robot to reduce scan frequency and improve navigation efficiency while maintaining adequate map reliability through targeted updates
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach results in more efficient, accurate mapping, reduced likelihood of erratic movements, and improved safety by enhancing the accuracy of the map and reducing phantom objects, allowing AMRs to navigate more effectively and safely.
Implementation Method 1
a light detection and ranging ('LiDAR') sensor may be used to measure distances to obstacles from the AMR
Data Source
AI summary
Disclosed herein are devices, methods, and systems for navigating and positioning an autonomous robot within a map of an environment. The system may obtain an occupancy grid associated with the environment around the robot, wherein the occupancy grid includes grid points of potential destinations for the robot. The system may determine, for each grid point of the grid points of potential destinations, a weight for the grid point based on a distance to the grid point from a predefined reference point and based on a directional deviation to the grid point, where the directional deviation comprises an angular difference between a current heading of the robot and an angular direction from the reference point toward the grid point. The system may select, based on the weight, a target point from among the grid points and generate a movement instruction associated with moving the robot toward the target point.