Occupancy State Detection Using Hidden Markov Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Reliable occupancy state detection in vehicle environments is complex and requires high computational effort, making it challenging to accurately determine whether an area is occupied and, if so, its valid occupancy state.
Innovation Solution
A computer-implemented method using a Hidden Markov Model (HMM) to determine the probability distribution of occupancy states in an area over time, based on measurement data from sensors like radar and LIDAR, and transition probabilities between states.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional occupancy state detection methods are used, then measurement accuracy can be maintained, but computational complexity and processing time increase significantly
Solution Approach 1:
The occupancy detection problem is segmented into discrete occupancy states (free space, static occupied, dynamic occupied, and uncertainty states). By dividing the continuous occupancy probability space into distinct segments, the system can use discrete probability distributions and transition models, significantly reducing computational complexity while maintaining detection accuracy.
Solution Approach 2:
The patent transforms the occupancy detection problem from direct classification to probability distribution estimation over discrete states. By changing the parameter representation from deterministic labels to probabilistic state distributions, the system achieves more efficient computation through dynamic programming and transition probability models.
2Reliability
If traditional occupancy state detection methods are used, then detection capability is maintained, but processing speed decreases due to high computational effort
Solution Approach 1:
The system pre-defines discrete occupancy states and transition probability models before actual detection. By preparing the state space and transition matrices in advance, the real-time detection process only requires computing probability updates using efficient algorithms, significantly improving processing speed while maintaining reliable detection.
Solution Approach 2:
The patent uses recursive probability update equations that continuously refine occupancy state estimates based on new sensor measurements. This continuous action approach allows the system to maintain reliable detection by constantly updating state probabilities without requiring complete re-computation, thereby improving processing efficiency.
3Measurement precision
If detailed occupancy state classification is implemented, then detection accuracy improves, but system complexity increases
Solution Approach 1:
The patent introduces discrete occupancy states as intermediary categories between raw sensor data and final detection results. These intermediate states (free space, static occupied, dynamic occupied, and four uncertainty states) serve as a structured bridge that simplifies the classification process while maintaining detailed detection accuracy through probability distributions.
Solution Approach 2:
The system adds a probabilistic dimension to occupancy state classification by representing each state with a probability distribution rather than simple binary labels. This dimensional transformation allows detailed classification accuracy while managing system complexity through structured probability models and transition matrices.
Data Source
AI summary
A computer-implemented method for occupancy state detection in an area for a pre-determined point in time. In aspects, the computer-implemented method includes operations carried out by computer hardware components. The operations include determining a probability distribution over a list of possible occupancy states of the area at a previous point in time, determining measurement data related to the area at the pre-determined point in time, and determining a probability distribution over the list of possible occupancy states of the area at the pre-determined point in time based on the measurement data and the probability distribution over the list of possible occupancy states of the area at the previous point in time.