Quality and Budget-Oriented Task Offloading for Vehicular Cooperative Perception Using Reinforcement Learning
Bibliographic record
Abstract
Task offloading in Vehicular Edge Computing (VEC) is crucial for enhancing cooperative perception (CP) in Autonomous Vehicles (AVs), thereby improving traffic situational awareness. However, existing approaches often neglect the balance between high-quality execution of interdependent tasks and conserving AVs limited budget, including communication and financial resources. To address this, we propose the Quality and Budget-Aware Task Offloading (QBATO) framework. QBATO is the first framework to balance the quality of cooperative perception with budget conservation. QBATO models the budget as a queue to ensure stability, balancing resource use while prioritizing situational awareness in CP. Additionally, QBATO enhances CP quality by predicting vehicles movements and estimating their regions of interest, thereby improving the Value of Information (VOI). The task offloading problem is modeled as a Quadratic Multiple Knapsack Problem (QMKP), an NPhard problem that optimizes vehicle allocation by evaluating the quality of assigning multiple vehicles to the same worker through a quadratic objective function.To manage resources effectively, we apply the queue stability Lyapunov drift-minus-bonus approach. We also introduce the QBATO-Heuristic (QBATO-H), which solves the problem in a decentralized, time-efficient manner using a multi-agent deep reinforcement learning technique that leverages the Q-Mixing Network (QMIX) method, which employs monotonic value decomposition to coordinate the actions of multiple agents. Extensive evaluations show that QBATO outperforms prominent quality and budget-oblivious schemes by up to 49%, 15%, and 35% in terms of budget conservation, situational awareness, and efficiency, respectively. QBATO-H also yields a small gap of up to 7% and 11% with QBATO in terms of budget conservation and efficiency, respectively.
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 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 | 0.002 | 0.007 |
| 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 | 0.001 |
| Open science | 0.004 | 0.007 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".