2022 Fiscal Year Research-status Report
Driver-automation mutual adaptation: modeling, design, and evaluation of haptic interface for cooperative driving tasks
| Project/Area Number |
21K17781
|
|---|
| Research Institution | The University of Tokyo |
|---|
Principal Investigator |
王 正 東京大学, 生産技術研究所, 特任助教 (20837497)
|
|---|
| Project Period (FY) |
2021-04-01 – 2024-03-31
|
| Keywords | HMI / Automated driving / Driver behavior modeling / Human-centered design / Machine learning / Intelligent vehicles |
|---|
| Outline of Annual Research Achievements |
Our research focuses on driver-automation mutual adaptation for haptic shared control.
In FY 2022, our research achievements are summarized as follows:
1. A driver model was developed using a deep learning network and was trained on data collected from a driving simulator experiment with nine participants, and is demonstrated to be effective in predicting individual driver's target trajectory. The driver model is applied for further design of shared control.
2. An adaptive control allocation algorithm was developed for lane keeping under an indirect shared control framework. The algorithm uses a trust-based data-driven shared control strategy and blends control inputs of drivers and automation. The automated control agent is computed using Koopman model predictive control. Adaptive control authority allocation is achieved using a hybrid human-to-machine trust model based on a trust mechanism inferred from human-automation interaction and driver input intention. The proposed algorithm is demonstrated to be effective and beneficial in an interactive simulation environment with five participants.
3. A steering assistance system involving a shared control strategy was developed for driver override in automated vehicles. The system considers the potential driver demand for override when the vehicle initiates a fail-safe maneuver. A shared control strategy based on driver controllability is adopted to smoothly transfer driving authority when the vehicle is out of danger. The effectiveness of the proposed system is demonstrated in multi-lane highway scenarios.
|
| Current Status of Research Progress |
Current Status of Research Progress
3: Progress in research has been slightly delayed.
Reason
1. An adaptive control allocation algorithm for shared lane keeping using a trust-based data-driven strategy and Koopman model predictive control is developed and demonstrated to be effective in an interactive driving simulation with five participants.
2. A steering assistance system that takes into account the potential driver demand during a fail-safe maneuver and includes a shared control strategy based on driver controllability to smoothly transfer driving authority when the vehicle is out of danger, is developed, and the effectiveness of the proposed system is demonstrated in multi-lane highway scenarios.
3. The high-fidelity driving simulator experiments to evaluate the proposed adaptive shared control algorithm were designed, while they were not smoothly carried out as planned due to COVID-19.
|
| Strategy for Future Research Activity |
In the next fiscal year, our research activities will focus on the following aspects:
1. A Personalized Predictive Haptic Steering Assistance system will be verified in a high-fidelity driving simulator experiment by developing individualized methods for predicting intention more accurately, finding the suitable haptic supporting torque, and enhancing the adaptability and user experience of the system.
2. Based on results obtained in the preliminary experiment which focuses on adaptive shared control using a trust-based data-driven strategy and Koopman model predictive control, a new method to update trust-based data-driven strategy which takes the minimum trust value with more appropriate time steps will be developed.
3. Driving simulator experiments will be designed and conducted to collect gaze data in takeover scenarios, followed by correlation analysis between gaze data and driver behavior, construction of models for intention recognition and situation awareness measurement, and a further experiment to verify the improved shared control system for the fail-safe maneuver in L4 Driving Automation.
|
| Causes of Carryover |
In this fiscal year, we have focused on system design and evaluation by interactive simulation experiments. The high-fidelity driving simulator experiments were postponed due to COVID-19. In the next fiscal year, we will conduct high-fidelity driving simulator experiments by recruiting subjects. In addition, we will publish several journal papers to report our results, and therefore, budget for publication fee will be needed.
|
