Robot Path Planning Using 4D Lattice and JPDAF Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing robot path planning technologies face challenges in real-time data acquisition and efficient obstacle avoidance in dynamic environments, leading to prolonged detection times and suboptimal path planning.
Innovation Solution
A method involving a Time Of Flight sensor to generate depth maps, a binary large object algorithm for object detection, and a Joint Probability Data Association Filter to predict object positions and shapes, allowing for the creation of a path that minimizes collision risks by calculating distance and obstacle costs in a 3D lattice-based space.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If 3D data is acquired using sensors to detect obstacles, then the robot can recognize obstacle positions and plan paths, but the detection time becomes too long to achieve real-time path planning
Solution Approach 1:
The patent segments the 3D space into a lattice structure with discrete cells, transforming continuous space into discrete units. This segmentation allows the robot to process spatial information in manageable discrete cells rather than continuous coordinates, reducing computational complexity and detection time while maintaining accurate obstacle position recognition through depth map analysis of each lattice cell
Solution Approach 2:
The patent performs preliminary actions by pre-dividing the space into lattices and pre-processing depth map data to identify occupied and free cells before actual path planning. The JPDAF algorithm also performs preliminary prediction of obstacle positions based on historical data, allowing the robot to have advance information about potential obstacles and plan paths more efficiently without waiting for complete real-time detection
2Reliability
If the robot plans a path avoiding moving obstacles in dynamic space, then collision avoidance is achieved, but the path planning complexity increases significantly
Solution Approach 1:
The patent adds the time dimension to the traditional 3D spatial lattice, creating a 4D space-time lattice for path planning. This dimensional extension allows the robot to consider obstacle movement trajectories and predict future positions, achieving reliable collision avoidance in dynamic environments. The JPDAF algorithm leverages this additional dimension to perform probabilistic prediction of obstacle positions based on historical data, managing the increased complexity through structured temporal-spatial reasoning
Solution Approach 2:
The patent introduces the JPDAF algorithm as an intermediary between raw sensor data and path planning decisions. This intermediary component processes depth map information, predicts obstacle positions and trajectories, and provides probabilistic occupancy information to the path planning module. By inserting this intelligent intermediary layer, the system manages planning complexity while maintaining high collision avoidance reliability through probabilistic reasoning about dynamic obstacles
3Productivity
If high-speed data acquisition is performed to detect moving objects, then real-time detection is achieved, but the system consumes excessive computational resources
Solution Approach 1:
The patent segments the detection space into a lattice structure with discrete cells, allowing the system to process only relevant spatial regions rather than analyzing the entire environment continuously. This segmentation enables high-speed detection by focusing computational resources on occupied cells and their neighbors, reducing overall energy consumption while maintaining real-time detection capability through efficient depth map processing of segmented regions
Solution Approach 2:
The patent applies partial action by performing detection and path planning only in necessary regions of the lattice space rather than uniformly processing the entire environment. The system focuses computational effort on cells that are occupied or adjacent to occupied cells, using the JPDAF algorithm to predict and monitor only relevant obstacle trajectories. This selective partial processing achieves real-time detection performance with reduced energy consumption compared to exhaustive full-space analysis
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
Enables the robot to efficiently plan an optimal path in real-time while avoiding obstacles, reducing detection time and improving path planning accuracy.
Implementation Method 1
A method involving a Time Of Flight sensor to generate depth maps
Data Source
AI summary
A robot and a method for creating a robot path. The method for planning the robot path includes generating a depth map including a plurality of cells by measuring a distance to an object, dividing a boundary among the plurality of cells into a plurality of partitions according to individual depth values of the cells, and extracting a single closed loop formed by the divided boundary, obtaining a position and shape of the object located at a first time through the extracted single closed loop, calculating a probability that the object is located at a second time after t seconds on the basis of the obtained position and shape of the object located at the first time, and creating a moving path simultaneously while avoiding the object according to the calculated probability, thereby creating an optimum path without colliding with the object.