End-to-End Autonomous Driving: An Angle Branched Network Approach
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Imitation learning for the end-to-end autonomous driving has drawn renewed attention from academic communities. Current methods either only use images as the input, which will yield ambiguities when a vehicle approaches an intersection, or use additional command information to navigate the vehicle but inefficiently. Focusing on making the vehicle automatically drive along the given path, we propose a new and effective navigation command called as subgoal angle which does not require human participation and is calculated by the current position and subgoal of the ego-vehicle. Thus, the subgoal angle contains more information than the navigation command represented as a one-hot vector. Additionally, we propose a model architecture called as angle branched network that makes predictions based on the subgoal angle. In this network, the subgoal angle is not only used for extracting useful features but also for guiding the appropriate prediction layer to make predictions for both the steer angle and the throttle status (which controls the acceleration). Experiments are conducted in a three-dimensional urban simulator. Both quantitive and qualitive results show the effectiveness of the navigation command and the angle branched network. Moreover, the performance can be further boosted by integrating both semantic and depth information into the driving model. Especially by using the depth information, collisions with vehicles and pedestrians can be reduced.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.001 |
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 it