2021 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 – 2023-03-31
|
| Keywords | Shared control / Driver behavior modeling / Haptic interface / Mutual adaptation / Automated driving / HMI |
|---|
| Outline of Annual Research Achievements |
Our research focuses on driver-automation mutual adaptation with haptic interface.
In FY 2021, our research achievements are summarized as follows:
1. Through a driving simulator experiment with a number of subjects, a lateral control model of human driver was developed by combining long short-term memory network and neuromuscular dynamics for lane change maneuver in a pedestrian collision avoidance situation. The results show that the developed data-driven model has higher identification accuracy than traditional model with two look-ahead points and neuromuscular dynamics.
2. A model predictive control based mutual adaptation shared control algorithm was developed and its effectiveness on take-over control for collision avoidance during automated driving was verified by numerical simulations.
3. A comprehensive literature review on physiological measurement for personalization in automated driving was conducted and provided as a resource to further driver-automation interaction development.
|
| Current Status of Research Progress |
Current Status of Research Progress
3: Progress in research has been slightly delayed.
Reason
1. A driving simulator experiment with a number of participants was conducted to collect the driving data, which are used to analyze the driver
behavior when driving with haptic steering interface, and a data-driven driver model was developed.
2. A mutual adaptation shared control algorithm was proposed by having driver model embedded within the control loop and tested by comparing with the conditions of manual control and benchmark controller in numerical simulations.
3. A high-fidelity driving simulator experiment to evaluate the proposed shared control algorithm was designed, while it was 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. The designed algorithm of mutual adaption shared control will be investigated in take-over control situations for collision avoidance by high-fidelity driving simulator experiments.
2. A real vehicle experiment will be prepared and conducted to validate the effect of the developed shared control system on reducing driver workload and improving driver acceptance.
3.The driving performance measured in the driving simulator and real-vehicle experiments will be analyzed by data-driven approach to provide more insightful understanding of driver behavior under shared control.
|
| Causes of Carryover |
In this fiscal year, we have focused on driver model development, numerical simulation, and designing driving simulator experiments. Thus, we hired research assistant for data analysis and payed publication fees. Meanwhile, due to covid-19, we used relatively less money for the travel. In the next fiscal year, we will conduct driving experiments by recruiting subjects, and will spend travel expense to present the findings.
|
