A Survey on Approximate Edge AI for Energy Efficient Autonomous Driving Services
arXiv:2304.14271 · doi:10.1109/COMST.2023.3302474
Abstract
Autonomous driving services rely heavily on sensors such as cameras, LiDAR, radar, and communication modules. A common practice of processing the sensed data is using a high-performance computing unit placed inside the vehicle, which deploys AI models and algorithms to act as the brain or administrator of the vehicle. The vehicular data generated from average hours of driving can be up to 20 Terabytes depending on the data rate and specification of the sensors. Given the scale and fast growth of services for autonomous driving, it is essential to improve the overall energy and environmental efficiency, especially in the trend towards vehicular electrification (e.g., battery-powered). Although the areas have seen significant advancements in sensor technologies, wireless communications, computing and AI/ML algorithms, the challenge still exists in how to apply and integrate those technology innovations to achieve energy efficiency. This survey reviews and compares the connected vehicular applications, vehicular communications, approximation and Edge AI techniques. The focus is on energy efficiency by covering newly proposed approximation and enabling frameworks. To the best of our knowledge, this survey is the first to review the latest approximate Edge AI frameworks and publicly available datasets in energy-efficient autonomous driving. The insights and vision from this survey can be beneficial for the collaborative driving service development on low-power and memory-constrained systems and also for the energy optimization of autonomous vehicles.
References in corpus (25)
- Lidar for Autonomous Driving: The principles, challenges, and trends for automotive lidar and perception systems
- A Survey on Edge Computing Systems and Tools
- Direct Feedback Alignment Provides Learning in Deep Neural Networks
- DeepFactors: Real-Time Probabilistic Dense Monocular SLAM
- One Million Scenes for Autonomous Driving: ONCE Dataset
- IPOD: Intensive Point-based Object Detector for Point Cloud
- Forecasting the Impact of Connected and Automated Vehicles on Energy Use A Microeconomic Study of Induced Travel and Energy Rebound
- Combining Deep Reinforcement Learning and Safety Based Control for Autonomous Driving
- The StreetLearn Environment and Dataset
- A Commute in Data: The comma2k19 Dataset
- SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving
- DurLAR: A High-fidelity 128-channel LiDAR Dataset with Panoramic Ambient and Reflectivity Imagery for Multi-modal Autonomous Driving Applications
- PI-Edge: A Low-Power Edge Computing System for Real-Time Autonomous Driving Services
- RACECAR -- The Dataset for High-Speed Autonomous Racing
- Highway Driving Dataset for Semantic Video Segmentation
- Learning Low-Rank Approximation for CNNs
- KDLSQ-BERT: A Quantized Bert Combining Knowledge Distillation with Learned Step Size Quantization
- 6G V2X Technologies and Orchestrated Sensing for Autonomous Driving
- A Quantized Representation of Probability in the Brain
- FedPAGE: A Fast Local Stochastic Gradient Method for Communication-Efficient Federated Learning
- Next Generation Opportunistic Networking in Beyond 5G Networks
- Single-shot Channel Pruning Based on Alternating Direction Method of Multipliers
- AUSN: Approximately Uniform Quantization by Adaptively Superimposing Non-uniform Distribution for Deep Neural Networks
- Exploring Neural Networks Quantization via Layer-Wise Quantization Analysis
- The NEOLIX Open Dataset for Autonomous Driving