Integer Occupancy Grid Perception for Embedded Robotics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing multi-sensor fusion methods for occupancy grids in robotics require complex floating-point calculations, leading to high computing power and energy consumption, which is not suitable for on-board systems in robots and autonomous vehicles.
Innovation Solution
The method makes the calculation of occupancy probabilities context-dependent by using an a priori probability value that can be manually set, transmitted, or calculated based on environmental factors, allowing for integer calculations to construct a consolidated occupancy grid without increasing real-time computational complexity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If floating-point calculations are used for occupancy grid multi-sensor fusion, then measurement precision and reliability are improved, but computing power requirements and energy consumption increase significantly
Solution Approach 1:
The patent transforms the computational parameters from floating-point to integer domain. By reformulating the occupancy probability calculations using integer arithmetic operations instead of floating-point operations, the system maintains measurement precision while dramatically reducing energy consumption and computational complexity suitable for embedded robotic systems
Solution Approach 2:
The patent substitutes the computational mechanism by replacing floating-point arithmetic operations with integer arithmetic operations. This substitution eliminates the need for complex floating-point hardware units while achieving equivalent computational results through integer-based probability calculations
2Measurement precision
If floating-point calculations are used for occupancy grid multi-sensor fusion, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent changes the numerical parameter representation from floating-point to integer format. This parameter transformation simplifies the processor architecture requirements, eliminating the need for complex floating-point units (FPUs) while maintaining sufficient precision for occupancy grid calculations through integer arithmetic
Solution Approach 2:
The patent replaces the mechanical computational system by substituting floating-point arithmetic operations with integer arithmetic operations. This substitution simplifies the processor design by using basic integer arithmetic units instead of complex floating-point hardware, reducing device complexity while preserving calculation accuracy
3Measurement precision
If floating-point calculations are used for occupancy grid multi-sensor fusion, then measurement precision is improved, but productivity decreases due to higher computational requirements
Solution Approach 1:
The patent transforms computational parameters from floating-point to integer domain, enabling faster processing speeds. Integer arithmetic operations execute more quickly than floating-point operations, improving productivity and real-time processing capability while maintaining adequate precision for occupancy grid applications
Solution Approach 2:
The patent substitutes the computational mechanism by replacing floating-point arithmetic with integer arithmetic. This substitution improves processing speed and productivity by using simpler, faster integer operations that can be executed efficiently on standard embedded processors without specialized floating-point hardware
Data Source
Figure 1~3
Figure 4~5A
Figure 5B~5C
AI summary
A method for perceiving material bodies comprising the following steps: a) Acquisition of a plurality of distance measurements of said material bodies from one or more sensors (C1 ...CNC); b) Acquisition or calculation of a priori occupancy probability value (P(o)) of the cells of an occupancy grid; and c) Application of an inverse sensor model on said occupancy grid to determine an occupancy probability of a set of cells of said grid; d) Construction of a consolidated occupancy grid by merging the occupancy probabilities estimated in step c); characterized in that each said inverse sensor model is a discrete model, associating to each cell of the corresponding occupancy grid, and for each distance measurement, a probability class chosen within the same set of finite cardinality and identified by an integer index; and in that said step d) is implemented by means of integer calculations performed on the indices of the probability classes determined in said step c), and as a function of said prior occupancy probability value.A system for perceiving material bodies adapted to implement such a process.