18269443. DRIVING EVALUATION SYSTEM, LEARNING DEVICE, EVALUATION RESULT OUTPUT DEVICE, METHOD, AND PROGRAM simplified abstract (NEC Corporation)
Contents
- 1 DRIVING EVALUATION SYSTEM, LEARNING DEVICE, EVALUATION RESULT OUTPUT DEVICE, METHOD, AND PROGRAM
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 DRIVING EVALUATION SYSTEM, LEARNING DEVICE, EVALUATION RESULT OUTPUT DEVICE, METHOD, AND PROGRAM - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Original Abstract Submitted
DRIVING EVALUATION SYSTEM, LEARNING DEVICE, EVALUATION RESULT OUTPUT DEVICE, METHOD, AND PROGRAM
Organization Name
Inventor(s)
DRIVING EVALUATION SYSTEM, LEARNING DEVICE, EVALUATION RESULT OUTPUT DEVICE, METHOD, AND PROGRAM - A simplified explanation of the abstract
This abstract first appeared for US patent application 18269443 titled 'DRIVING EVALUATION SYSTEM, LEARNING DEVICE, EVALUATION RESULT OUTPUT DEVICE, METHOD, AND PROGRAM
Simplified Explanation
The function input means accepts input of a cost function expressed as a linear sum of terms in which each feature indicating driving of a driver is weighted by a degree of emphasis. The learning means learns the cost function for each area by inverse reinforcement learning using expert driving data as training data that includes information representing contents of driving of an expert collected for each area. The driving data input means accepts input of user driving data including information indicating driving of a subject whose driving is evaluated, information indicating environment when driving, and position information where these pieces of information were obtained. The evaluation means identifies an area where a user drives from the position information, selects the cost function corresponding to the area, applies the information indicating the environment when the subject drives to the selected cost function to estimate the driving of the expert in the same environment, and outputs an evaluation result comparing estimated driving of the expert with the driving of the subject.
- The innovation involves accepting input of cost functions and learning them through expert driving data.
- The system evaluates user driving data by comparing it with estimated expert driving in the same environment.
Potential Applications
This technology could be applied in:
- Autonomous driving systems
- Driver training programs
Problems Solved
This technology helps in:
- Evaluating driving skills objectively
- Providing personalized feedback to drivers
Benefits
The benefits of this technology include:
- Improved driving performance
- Enhanced safety on the roads
Potential Commercial Applications
Optimizing driving performance assessment for:
- Automotive companies
- Driving schools
Unanswered Questions
How does this technology handle variations in driving styles among different drivers?
Can this technology be adapted for other types of vehicle operations, such as flying drones or operating heavy machinery?
Original Abstract Submitted
The function input means accepts input of a cost function expressed as a linear sum of terms in which each feature indicating driving of a driver is weighted by a degree of emphasis. The learning means learns the cost function for each area by inverse reinforcement learning using expert driving data as training data that includes information representing contents of driving of an expert collected for each area. The driving data input means accepts input of user driving data including information indicating driving of a subject whose driving is evaluated, information indicating environment when driving, and position information where these pieces of information were obtained. The evaluation means identifies an area where a user drives from the position information, selects the cost function corresponding to the area, applies the information indicating the environment when the subject drives to the selected cost function to estimate the driving of the expert in the same environment, and outputs an evaluation result comparing estimated driving of the expert with the driving of the subject.