Visual Detection and Deep Reinforcement Learning-Based Car Following and Energy Management for Hybrid Electric Vehicles
Bibliographic record
Abstract
Practical vision-based technology is essential for the autonomous driving of intelligent hybrid electric vehicles. In this article, a hierarchical control structure is proposed, which combines you only look once-based object detection and learning-based intelligent control by deep reinforcement learning. After modeling a typical car-following scene, the leading car is detected in the driving image, and the real-time distance between two cars is evaluated by vision-based distance measurement. Then, a deep Q-network is adopted to learn the car-following control strategy and energy management strategy, which achieves multiobjective control of the hybrid powertrain while maintaining a reasonable distance for the following car. When completing off-line training, the online processor-in-the-loop test by the edge computing device NVIDIA Jetson AGX Xavier is performed. Results show that the hierarchical control strategy gets a fuel economy of 5.76 L/100 km while keeping a safe following distance. Moreover, the time consumed to run a driving cycle of 1797 s in the embedded device is 476.87 s, which means that a control loop, including target recognition, distance measurement, car-following control, and energy management, takes 0.26 s. This study proves that vehicle vision can lay the technical foundation for intelligent driving, and the results illustrate that the hierarchical control structure is capable of achieving considerable computing efficiency on embedded devices and has the potential for real vehicle control.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".