Adaptive Occupancy Grid Scanning for Region-of-Interest Perception
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing probabilistic occupancy grid-based perception methods for robots and autonomous vehicles require significant computing power and struggle to optimize spatiotemporal resolution and resource usage in dynamic environments.
Innovation Solution
Adaptive control of a steerable distance sensor's detection region, dynamically adjusting its width and orientation to focus on 'regions of interest' with higher spatial and temporal resolution, using Bayesian fusion and integer calculations for efficient resource utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If uniform scanning is performed with a sensor, then the entire environment is covered, but the computing power required increases significantly and spatiotemporal resolution cannot be optimized
Solution Approach 1:
The patent applies local quality by differentiating the scanning resolution across different spatial regions. Regions of interest (such as areas with detected objects or boundaries) are scanned with higher spatial and temporal resolution using narrower detection regions, while other areas use wider detection regions with lower resolution. This allows the system to optimize measurement precision where needed while reducing computing power requirements in less critical areas.
Solution Approach 2:
The patent implements dynamics by making the detection region width adaptive rather than fixed. The system dynamically adjusts the angular width of the detection region based on the identified regions of interest, narrowing the beam for detailed scanning of critical areas and widening it for broader coverage in less critical areas. This dynamic adaptation enables optimization of both measurement precision and computing power consumption.
2Measurement precision
If the detection region width is reduced to improve spatial resolution, then measurement precision increases, but the scanning time increases and productivity decreases
Solution Approach 1:
The patent applies local quality by assigning different detection region widths to different spatial regions based on their importance. High-priority regions (regions of interest) receive narrow detection regions for high spatial resolution, while low-priority regions receive wide detection regions for faster scanning. This resolves the contradiction by ensuring high precision only where necessary, thereby maintaining overall scanning productivity.
Solution Approach 2:
The patent applies partial action by performing high-resolution scanning only on partial regions (regions of interest) rather than the entire environment. The system identifies and focuses computational resources on scanning only those areas that require detailed measurement, while using coarser scanning for the remainder of the environment, thus improving productivity without sacrificing necessary precision.
3Productivity
If the detection region width is increased to improve scanning speed, then productivity increases, but measurement precision and spatial resolution deteriorate
Solution Approach 1:
The patent applies local quality by varying the detection region width according to spatial location and importance. Wide detection regions are used in low-priority areas to maintain high scanning speed, while narrow detection regions are applied in high-priority regions of interest to ensure adequate measurement precision. This spatially differentiated approach resolves the contradiction between speed and precision.
4Adaptability or versatility
If the sensor scans the entire environment uniformly, then complete environmental coverage is achieved, but resource usage increases and cannot be optimized for dynamic environments
Solution Approach 1:
The patent applies preliminary action by first performing a preliminary scan or using prior knowledge to identify regions of interest before conducting detailed scanning. This preliminary identification allows the system to pre-determine which areas require high-resolution scanning, thereby optimizing resource usage in dynamic environments by focusing computational and sensing resources only where needed rather than uniformly across the entire environment.
Solution Approach 2:
The patent implements dynamics by making the scanning strategy adaptive to environmental conditions. The system continuously identifies regions of interest based on detected objects, boundaries, or other relevant features, and dynamically adjusts the detection region width and scanning frequency accordingly. This dynamic adaptation enables the system to optimize resource usage in response to changing environmental conditions while maintaining complete environmental coverage.
Data Source
Figure 1~2
Figure 3~4
Figure 5~6
AI summary
The invention relates to a method for perceiving physical bodies (CM) in an environment, comprising the following steps: a) in an acquisition sequence, operating a sensor (CD) having a detection region (RD) that can be oriented so as to acquire a plurality of distance measurements (MDi) in relation to said physical bodies; b) based on each of said distance measurements, determining a probability of occupancy by a physical body of a set of cells of an occupancy grid; and c) constructing a consolidated occupancy grid (GO) by carrying out Bayesian fusion on the probabilities of occupancy estimated in step b); characterized in that the detection region of the sensor has a variable angular width and in that the method also comprises the following steps: d) identifying, based on said occupancy grid, at least one region of interest (ROI) of the environment; and e) determining, based on the one or more regions of interest identified in step d), what is referred to as an acquisition sequence defining, for each distance measurement, at least the orientation (θ, φ) and the angular width (α) of the detection region of the sensor. The invention also relates to a system for implementing such a method.