An Integrated Lateral and Longitudinal Decision-Making Model forAutonomous Driving Based on Deep Reinforcement Learning
Bibliographic record
Abstract
Decision-making is an important component of autonomous driving perception, decision-making, planning, and control pipeline, which undertakes the task of how the ego vehicle makes high-level decision-making behaviors (such as lane change and car following) after sensing the environmental state, and then these high-level decision-making behaviors can be transmitted to the downstream planning and control module for specific low-level action execution. Based on the method of deep reinforcement learning (specifically, Deep Q network (DQN) and its variants), an integrated lateral and longitudinal decision-making model for autonomous driving is proposed in a multilane highway environment with both autonomous driving vehicle (ADV) and manual driving vehicle (MDV). The classic MOBIL and IDM models are used for the lateral and longitudinal decisions of MDV (i.e., lane changing and car following), while the lateral and longitudinal decisions of ADV are dominated by deep reinforcement learning models. In addition, this paper also uses the nonlinear kinematic bicycle model and two-point visual control model to realize the low-level control of both MDV and ADV. By setting a reasonable state, action, and reward function, this paper has carried out a large number of simulation experiments on the proposed autonomous driving decision-making model based on deep reinforcement learning in a three-lane road environment. The results show that under such scenario setting conditions, the deep reinforcement learning-based model proposed in this paper performs well in autonomous driving safety and travel efficiency. At the same time, when compared with the classical rule-based decision-making model (MOBIL&IDM), it is found that the model proposed in this paper can significantly achieve better results in episode rewards after stable training. In addition, through a large number of hyper-parameter tuning experiments, the performance of DQN, DDQN, and dueling DQN models, which are also deep reinforcement learning-based decision-making models, under different hyper-parametric configurations is compared and analyzed, which can provide a valuable reference for the specific scenario application of these models.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".