aiqbench analysis
This survey critically evaluates the trade-offs between Transformer-based architectures and their practical deployment in autonomous driving, focusing on latency, memory overhead, and energy consumption. It systematically reviews compression techniques like quantization and pruning as essential system-level design choices rather than mere post-processing steps to ensure robustness and safety. The article identifies key research directions for creating hardware-conscious evaluation standards that balance model capacity with real-world vehicle constraints.
Transformer-Based Autonomous Driving Models and Deployment-Oriented Compression: A Survey
arXiv:2304.10891v4 Announce Type: replace-cross Abstract: Transformer-based models are becoming a central paradigm in autonomous driving because they can capture long-range spatial dependencies, multi-agent interactions, and multimodal context across perception, prediction, and planning. At the same time, their deployment in real vehicles remains difficult because high-capacity attention-based architectures impose substantial latency, memory, and energy overhead. This survey reviews representative Transformer-based autonomous driving models and organizes them by task role, sensing configuration, and architectural design. More importantly, it examines these models from a deployment-oriented perspective and analyzes how efficiency constraints reshape model design choices in practice. We further review compression and acceleration strategies relevant to Transformer-based driving systems, including quantization, pruning, knowledge distillation, low-rank approximation, and efficient attention, and discuss their benefits, limitations, and task-dependent applicability. Rather than treating compression as an isolated post-processing step, we highlight it as a system-level design consideration that directly affects deployability, robustness, and safety. Finally, we identify open challenges and future research directions toward standardized, safety-aware, and hardware-conscious evaluation of efficient autonomous driving systems.
Abstract:Transformer-based models are becoming a central paradigm in autonomous driving because they can capture long-range spatial dependencies, multi-agent interactions, and multimodal context across perception, prediction, and planning. At the same time, their deployment in real vehicles remains difficult because high-capacity attention-based architectures impose substantial latency, memory, and energy overhead. This survey reviews representative Transformer-based autonomous driving models and organizes them by task role, sensing configuration, and architectural design. More importantly, it examines these models from a deployment-oriented perspective and analyzes how efficiency constraints reshape model design choices in practice. We further review compression and acceleration strategies relevant to Transformer-based driving systems, including quantization, pruning, knowledge distillation, low-rank approximation, and efficient attention, and discuss their benefits, limitations, and task-dependent applicability. Rather than treating compression as an isolated post-processing step, we highlight it as a system-level design consideration that directly affects deployability, robustness, and safety. Finally, we identify open challenges and future research directions toward standardized, safety-aware, and hardware-conscious evaluation of efficient autonomous driving systems.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO); Systems and Control (eess.SY)
arXiv:2304.10891 [cs.LG]
(or arXiv:2304.10891v4 [cs.LG] for this version)
Full text under the publisher's open licence · 189 words
Related coverage
Transformer-Based Autonomous Driving Models and Deployment-Oriented Compression: A Survey
arXiv · Jun 5, 2026
[AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)
Latent Space · Sep 17, 2026
[AINews] OpenAI reports Navier-Stokes singularity find in 88 hours using Astra-next, roughly 10,000 agents and 130B tokens (>$40M), a contender for second ever Millennium Prize awarded
Latent Space · Sep 9, 2026
Developing Healthcare Robotics with GPU-Native Medical Physics Simulation
NVIDIA · Jul 28, 2026