Abstract
Autonomous driving systems have attracted a significant amount of interest recently, and many industry leaders, such as Google, Uber, Tesla, and Mobileye, have invested a large amount of capital and engineering power on developing such systems. Building autonomous driving systems is particularly challenging due to stringent performance requirements in terms of both making the safe operational decisions and finishing processing at real-time. Despite the recent advancements in technology, such systems are still largely under experimentation and architecting end-to-end autonomous driving systems remains an open research question. To investigate this question, we first present and formalize the design constraints for building an autonomous driving system in terms of performance, predictability, storage, thermal and power. We then build an end-to-end autonomous driving system using state-of-the-art award-winning algorithms to understand the design trade-offs for building such systems. In our real-system characterization, we identify three computational bottlenecks, which conventional multicore CPUs are incapable of processing under the identified design constraints. To meet these constraints, we accelerate these algorithms using three accelerator platforms including GPUs, FPGAs, and ASICs, which can reduce the tail latency of the system by 169x, 10x, and 93x respectively. With accelerator-based designs, we are able to build an end-to-end autonomous driving system that meets all the design constraints, and explore the trade-offs among performance, power and the higher accuracy enabled by higher resolution cameras.
- J. Albericio, P. Judd, T. Hetherington, T. Aamodt, N. E. Jerger, and A. Moshovos. 2016. Cnvlutin: Ineffectual-Neuron-Free Deep Neural Network Computing 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA). 1--13. Google Scholar
Digital Library
- Jesse Levinson, Michael Montemerlo, and Sebastian Thrun. 2007. Map-Based Precision Vehicle Localization in Urban Environments. Robotics: Science and Systems (RSS), 2007.Google Scholar
Cross Ref
- Daofu Liu, Tianshi Chen, Shaoli Liu, Jinhong Zhou, Shengyuan Zhou, Olivier Teman, Xiaobing Feng, Xuehai Zhou, and Yunji Chen. 2015. PuDianNao: A Polyvalent Machine Learning Accelerator Proceedings of the Twentieth International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS '15). ACM, New York, NY, USA, 369--381. Google Scholar
Digital Library
- D. Mahajan, J. Park, E. Amaro, H. Sharma, A. Yazdanbakhsh, J. K. Kim, and H. Esmaeilzadeh. 2016. TABLA: A unified template-based framework for accelerating statistical machine learning 2016 IEEE International Symposium on High Performance Computer Architecture (HPCA). 14--26.Google Scholar
- Daniel V McGehee, Elizabeth N Mazzae, and GH Scott Baldwin. 2000. Driver reaction time in crash avoidance research: Validation of a driving simulator study on a test track. In Proceedings of the human factors and ergonomics society annual meeting, Vol. Vol. 44. SAGE Publications, 3--320.Google Scholar
Cross Ref
- Colin McManus, Winston Churchill, Ashley Napier, Ben Davis, and Paul Newman. 2013. Distraction suppression for vision-based pose estimation at city scales Robotics and Automation (ICRA), 2013 IEEE International Conference on. IEEE, 3762--3769.Google Scholar
- Matthew McNaughton, Chris Urmson, John M Dolan, and Jin-Woo Lee. 2011. Motion planning for autonomous driving with a conformal spatiotemporal lattice Robotics and Automation (ICRA), 2011 IEEE International Conference on. IEEE, 4889--4895.Google Scholar
- JM Miller, A Emadi, AV Rajarathnam, and M Ehsani. 1999. Current status and future trends in more electric car power systems Vehicular Technology Conference, 1999 IEEE 49th, Vol. Vol. 2. IEEE, 1380--1384.Google Scholar
- Mobileye. 2017. Autonomous Driving. https://www.mobileye.com/. (2017).Google Scholar
- Mobileye. 2017. Enabling Autonomous. http://www.mobileye.com/future-of-mobility/mobileye-enabling-autonomous/. (2017).Google Scholar
- Mobileye. 2017. Mobileye C2--270 Essentials. (2017).Google Scholar
- Mobileye. 2017. Mobileye CES 2017 Press Conference. (2017).Google Scholar
- Mihir Mody. 2016. ADAS Front Camera: Demystifying Resolution and Frame-Rate. EETimes. (2016).Google Scholar
- Raul Mur-Artal, Jose Maria Martinez Montiel, and Juan D Tardos. 2015. ORB-SLAM: a versatile and accurate monocular SLAM system. IEEE Transactions on Robotics Vol. 31, 5 (2015), 1147--1163.Google Scholar
Digital Library
- Ashley Napier and Paul Newman. 2012. Generation and exploitation of local orthographic imagery for road vehicle localisation. In Intelligent Vehicles Symposium (IV), 2012 IEEE. IEEE, 590--596.Google Scholar
Cross Ref
- Allen Newell and Stuart K Card. 1985. The prospects for psychological science in human-computer interaction. Human-computer interaction Vol. 1, 3 (1985), 209--242. Google Scholar
Digital Library
- David J Perreault and Vahe Caliskan. 2004. Automotive power generation and control. IEEE Transactions on Power Electronics Vol. 19, 3 (2004), 618--630.Google Scholar
Cross Ref
- Mihail Pivtoraiko, Ross A Knepper, and Alonzo Kelly. 2009. Differentially constrained mobile robot motion planning in state lattices. Journal of Field Robotics Vol. 26, 3 (2009), 308--333. Google Scholar
Digital Library
- Joseph Redmon and Ali Farhadi. 2016. YOLO9000: Better, Faster, Stronger. arXiv preprint arXiv:1612.08242 (2016).Google Scholar
- M. Rhu, N. Gimelshein, J. Clemons, A. Zulfiqar, and S. W. Keckler. 2016. vDNN: Virtualized deep neural networks for scalable, memory-efficient neural network design. In 2016 49th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO). 1--13. Google Scholar
Digital Library
- SAE International. 2014. AUTOMATED DRIVING, Levels of driving automation are defined in new SAE International standard J3016. http://www.sae.org/misc/pdfs/automated_driving.pdf. (2014).Google Scholar
- Erwin M Schau, Marzia Traverso, and Matthias Finkbeiner. 2012. Life cycle approach to sustainability assessment: a case study of remanufactured alternators. Journal of Remanufacturing Vol. 2, 1 (2012), 1--14.Google Scholar
Cross Ref
- Seagate Technology LLC. 2017. Seagate Desktop HDD Specification. http://www.seagate.com/consumer/upgrade/desktop-hdd/#specs. (2017).Google Scholar
- Shai Shalev-Shwartz, Shaked Shammah, and Amnon Shashua. 2016. Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving. NIPS Workshop on Learning, Inference and Control of Multi-Agent Systems (2016).Google Scholar
- H. Sharma, J. Park, D. Mahajan, E. Amaro, J. K. Kim, C. Shao, A. Mishra, and H. Esmaeilzadeh. 2016. From high-level deep neural models to FPGAs. In 2016 49th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO). 1--12. Google Scholar
Digital Library
- Alexander D Stewart and Paul Newman. 2012. Laps-localisation using appearance of prior structure: 6-dof monocular camera localisation using prior pointclouds. In Robotics and Automation (ICRA), 2012 IEEE International Conference on. IEEE, 2625--2632.Google Scholar
Cross Ref
- Jürgen Sturm, Nikolas Engelhard, Felix Endres, Wolfram Burgard, and Daniel Cremers. 2012. A benchmark for the evaluation of RGB-D SLAM systems Intelligent Robots and Systems (IROS), 2012 IEEE/RSJ International Conference on. IEEE, 573--580.Google Scholar
- TechCrunch. 2017. Intel buys Mobileye in $15.3B deal, moves its automotive unit to Israel. (2017).Google Scholar
- TechCrunch. 2017 b. Nvidia is powering the world's first Level 3 self-driving production car. (2017).Google Scholar
- TechCrunch. 2017 c. Waymo reveals completely homegrown sensor suite for Pacifica autonomous test car. (2017).Google Scholar
- Tesla. 2017. Full Self-Driving Hardware on All Cars. https://www.tesla.com/autopilot. (2017).Google Scholar
- Tesla Inc.. 2017. Tesla Autopilot: Full Self-Driving Hardware on All Cars. https://www.tesla.com/autopilot. (2017).Google Scholar
- Simon Thorpe, Denis Fize, Catherine Marlot, et almbox.. 1996. Speed of processing in the human visual system. nature Vol. 381, 6582 (1996), 520--522.Google Scholar
- Udacity. 2017. An Open Source Self-Driving Car. https://www.udacity.com/self-driving-car. (2017).Google Scholar
- Chris Urmson, Joshua Anhalt, Drew Bagnell, Christopher Baker, Robert Bittner, MN Clark, John Dolan, Dave Duggins, Tugrul Galatali, Chris Geyer, et almbox.. 2008. Autonomous driving in urban environments: Boss and the urban challenge. Journal of Field Robotics Vol. 25, 8 (2008), 425--466. Google Scholar
Digital Library
- U.S. Department of Transportation -- Federal Highway Administration. 2015. Highway Statistics 2015. https://www.fhwa.dot.gov/policyinformation/statistics.cfm. (2015).Google Scholar
- U.S. Department of Transportation -- National Highway Traffic Safety Administration. 2017. Federal Automated Vehicles Policy: Accelerating the Next Revolution in Roadway Safety. https://www.transportation.gov/AV. (2017).Google Scholar
- Velodyne. 2017. Velodyne HDL-64E LiDAR. http://velodynelidar.com/hdl-64e.html. (2017).Google Scholar
- Waymo. 2017. Introducing Waymo's suite of custom-built, self-driving hardware. (2017).Google Scholar
- Ryan W Wolcott and Ryan M Eustice. 2014. Visual localization within LIDAR maps for automated urban driving Intelligent Robots and Systems (IROS 2014), 2014 IEEE/RSJ International Conference on. IEEE, 176--183.Google Scholar
- Ryan W Wolcott and Ryan M Eustice. 2015. Fast LIDAR localization using multiresolution Gaussian mixture maps Robotics and Automation (ICRA), 2015 IEEE International Conference on. IEEE, 2814--2821.Google Scholar
- R. Yazdani, A. Segura, J. M. Arnau, and A. Gonzalez. 2016. An ultra low-power hardware accelerator for automatic speech recognition 2016 49th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO). 1--12. Google Scholar
Digital Library
- Ying C Yeh. 1996. Triple-triple redundant 777 primary flight computer Aerospace Applications Conference, 1996. Proceedings., 1996 IEEE, Vol. Vol. 1. IEEE, 293--307.Google Scholar
- Chen Zhang, Zhenman Fang, Peipei Zhou, Peichen Pan, and Jason Cong. 2016. Caffeine: Towards uniformed representation and acceleration for deep convolutional neural networks. In Computer-Aided Design (ICCAD), 2016 IEEE/ACM International Conference on. IEEE, 1--8. Google Scholar
Digital Library
- Ji Zhang and Sanjiv Singh. 2015. Visual-lidar odometry and mapping: Low-drift, robust, and fast Robotics and Automation (ICRA), 2015 IEEE International Conference on. IEEE, 2174--2181.Google Scholar
Index Terms
The Architectural Implications of Autonomous Driving: Constraints and Acceleration
Recommendations
The Architectural Implications of Autonomous Driving: Constraints and Acceleration
ASPLOS '18: Proceedings of the Twenty-Third International Conference on Architectural Support for Programming Languages and Operating SystemsAutonomous driving systems have attracted a significant amount of interest recently, and many industry leaders, such as Google, Uber, Tesla, and Mobileye, have invested a large amount of capital and engineering power on developing such systems. Building ...
Numerical Analysis of Tractor Accidents using Driving Simulator for Autonomous Driving Tractor
ICMRE'19: Proceedings of the 5th International Conference on Mechatronics and Robotics EngineeringAutonomous driving of automobiles is a hot research topic in recent years. The autonomous driving tractor also has been studied in the agricultural field as well as an autonomous driving automobile. On the other hand, tractor accidents frequently occur ...
Autonomous Driving: Investigating the Feasibility of Bimodal Take-Over Requests
Autonomous vehicles will need de-escalation strategies to compensate when reaching system limitations. Car-driver handovers can be considered one possible method to deal with system boundaries. The authors suggest a bimodal auditory and visual handover ...







Comments