PLATEAU
Driving Simulator
PLATEAU Driving Simulator will achieve zero accidents and resolve workforce shortages
Traffic and human flow data are reproduced on a digital twin using 3D city models.
More practical safe‑driving training can be conducted in an environment that accurately reflects the actual routes used by logistics operators.
Do you have any challenges like this?
- Driver shortage
- Training is highly person‑dependent, resulting in inconsistent quality.
- The lack of practical training creates a significant gap between training and actual workplace operations.
- The risk of accidents does not decrease easily.
Solve your challenge with a digital twin.
Reproduce training environments of real cities in simulation by combining 3D city models with traffic data.
Selection
Area / Four vehicle types by industry / Veteran or beginner driver
Training
Experience scenarios that reflect a variety of everyday situations.
Assessment / Management
Playback by third-party assessment and review / Training records
3つの特長
① 実在都市の再現
実際のルートで訓練可能。PLATEAUの3D都市モデルで街並み・地形を再現します。
② データによる評価
運転ログの可視化で、客観的なスコアリングとリプレイによる振り返りが可能です。
③ 柔軟な訓練設計
車種・レベル別に対応。ヒヤリハット再現や天候・時間の変更で多様なシナリオを設計できます。
Features
Training on realistic road environments
Streets and terrain are accurately reproduced using PLATEAU 3D city models, enabling training along realistic driving routes.
Training field
Currently, about 96 square kilometers in Saitama Prefecture are available as the simulation training field, and any city with PLATEAU data can be added as an expansion area.
Utilized across various fields
Logistics (Trucks)
Training and hazard prediction along delivery routes
Bus
Driving training assuming in‑service operation
Taxi
Training assuming in‑service operation and passenger interaction on local routes
Reproducing accident-prone locations
Users can design training scenarios tailored to their objectives, such as trainee experience levels or changes in weather and time.
Course
For beginners: Basic operation training scenario
For veterans: Hazard‑prediction scenario for near‑miss accidents
Time & Weather
Selection of time (daytime, night, etc.) and weather conditions (sunny, rainy, etc.) is available.
Eliminating human-dependent training
Scoring-based objective evaluation and a replay function allow users to review their driving performance.
In addition, visualizing the driving logs clearly highlights areas for improvement.
Selectable Introduction Types
| Item | Full package | Lite package | Controller package |
|---|---|---|---|
| Image |
|
|
|
| Immersion | High — Multi‑display dedicated setup | Medium — Compact simple setup | Standard — Standard monitor‑controller setup |
| Installation | Requires wide space | Compact size | Space-saving |
| Use | Education / Demonstration / Exhibition | Daily training | Trial / Easy training |
| Software price |
[Subscription price] Initial year: USD17,000 From the second year: USD6,800 [One‑time purchase price] USD30,000 |
||
| Hardware price | USD66,000 | USD40,000 | USD7,000 |
| * PC cost and shipping fee are required separately | |||
Validation allows confirmation of the effects.
To validate the effectiveness of this system, an experiment was conducted with the cooperation of drivers, trainers, and managers from different sectors, including cargo (trucks) and passenger (buses and taxis) transportation.
Assessment
- Cityscape close to the actual environment
- Educational value of near-miss scenarios
- High effectiveness of the replay function
Participants' comments
"Driving in familiar surroundings is highly valuable for training in observation and prediction."
"I can vividly recall real roads and drive with a strong sense of realism"
"Scenario events such as sudden pedestrian appearances at hazardous spots and irregular situations are effective for training."
"I was able to objectively recognize my driving habits from a third‑person perspective."
"I can also use it for instruction."
Benefits of introduction
- Efficient education— Repeated and standardized trainings
- Improved safety— Experiencing hazardous events safely
- Eliminate human dependence— Reducing variability through data‑based assessment
- Reduction of accidents— Advance experience of near‑miss incidents
- Data use— Cycle of analyzing and improving the driving log
Core Technology
A realistic training environment is created using CityGML data, traffic and pedestrian flow simulations, and the VR platform UC-win/Road.
今後の展開
- 全国展開— PLATEAU都市モデルの拡大に合わせたエリア拡張
- シナリオ拡張— 業種・目的に応じた教材の追加
- ビッグデータ活用— 運転ログの蓄積と分析の高度化
Assessment items
Sudden acceleration / braking / steering
Passing on wide roads / Priority to the oncoming vehicle when the obstacle is on the driver’s side
Passing with sufficient clearance / Speed when passing through narrow spaces
Slow driving
Distance keeping / slow driving / priority to pedestrians
Temporary stop before a railway crossing