Robot Route Planning Using Reliability-Aware Velocity Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional route determining devices for robots often fail to accurately predict pedestrian movements, leading to frequent interference and reduced marketability, especially in congested traffic environments.
Innovation Solution
A route determining device that uses a predicted route algorithm, reliability calculation, and dynamic window approach to determine the optimal route and movement velocity of a robot, taking into account the distance and velocity of traffic participants, while employing a neural network to model prediction errors and reduce calculation load.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a predicted route algorithm is used to avoid interference with traffic participants, then the robot can navigate safely, but the robot stops frequently when predictions are inaccurate
Solution Approach 1:
The system dynamically adjusts the movement velocity command based on the calculated reliability of the predicted route. When reliability is high, the robot follows the predicted route closely; when reliability is low, the system modifies the velocity command to avoid potential interference, thus adapting to changing traffic conditions and prediction confidence levels
Solution Approach 2:
The system changes the parameter of movement velocity based on the reliability parameter of the predicted route. By calculating reliability and using it to determine an appropriate movement velocity command, the system optimizes both safety and continuity of movement, reducing frequent stops while maintaining avoidance of traffic participants
2Reliability
If the robot maintains a large distance from traffic participants to avoid interference, then safety is improved, but the robot's movement freedom and speed are reduced
Solution Approach 1:
The system dynamically determines the movement velocity command based on real-time reliability calculations of the predicted route and current traffic participant distances. This allows the robot to move at higher speeds when the predicted route is reliable and traffic participants are distant, while reducing speed only when necessary to maintain safety
Solution Approach 2:
The system optimizes the balance between distance to traffic participants and movement velocity by using reliability-based velocity commands. The target function considers both distance and velocity as variables, finding the optimal combination that maximizes speed while maintaining adequate safety distances
3Measurement precision
If complex prediction algorithms are used to improve route accuracy, then interference avoidance is improved, but calculation time and processing load increase
Solution Approach 1:
The system extracts only the essential elements needed for reliable route prediction and focuses calculation resources on determining the reliability of the predicted route and calculating the optimal movement velocity command. This selective approach maintains prediction accuracy while reducing unnecessary computational overhead
Solution Approach 2:
The system changes the approach from using complex algorithms to continuously adjusting movement parameters based on reliability calculations. By focusing computational effort on reliability assessment and velocity optimization rather than overly complex prediction models, the system achieves good prediction precision with reduced calculation time
Data Source
AI summary
This disclosure provides a route determining device capable of determining a route of a moving device such that the moving device smoothly moves to a destination while avoiding an interference with a traffic participant even in a congested traffic environment. A route determining device 1 determines a provisional movement velocity command v_cnn such that an interference between a robot 2 and traffic participants is avoided using the CNN, determines a distance dist between the robot 2 and the traffic participant closest to the robot 2 when the robot is assumed to move from the current position by a command v_cnn in accordance with the reliability P of the command v_cnn, and determines a movement velocity command v of the robot using a DWA such that a target function G including the distance dist and the movement velocity command v of the robot as independent variables has a maximum value.