Autonomous vehicles (AV) are expected to revolutionize transportation and improve road safety significantly. However, these benefits do not come without cost; AVs require large Deep-Learning (DL) models and powerful hardware platforms to operate reliably in real-time, requiring between several hundred watts to one kilowatt of power. This power consumption can dramatically reduce vehicles’ driving range and affect emissions. To address this problem, we propose SAGE: a methodology for selectively offloading the key energy-consuming modules of DL architectures to the cloud to optimize edge, energy usage while meeting real-time latency constraints. Furthermore, we leverage Head Network Distillation (HND) to introduce efficient bottlenecks within the DL architecture in order to minimize the network overhead costs of offloading with almost no degradation in the model’s performance. We evaluate SAGE using an Nvidia Jetson TX2 and an industry-standard Nvidia Drive PX2 as the AV edge, devices and demonstrate that our offloading strategy is practical for a wide range of DL models and internet connection bandwidths on 3G, 4G LTE, and WiFi technologies. Compared to edge-only computation, SAGE reduces energy consumption by an average of 36.13% , 47.07% , and 55.66% for an AV with one low-resolution camera, one high-resolution camera, and three high-resolution cameras, respectively. SAGE also reduces upload data size by up to 98.40% compared to direct camera offloading.
more »
« less
Carpooling and the Economics of Self-Driving Cars
We study the interplay between autonomous transportation, carpooling, and road pricing. We discuss how improvements in these technologies, and interactions among them, will affect transportation markets. Our main results show how to achieve socially effiient outcomes in such markets, taking into account the costs of driving, road capacity, and commuter preferences. An important component of the efficient outcome is the socially optimal matching of carpooling riders. Our approach shows how to set road prices and how to share the costs of driving and tolls among carpooling riders in a way that implements the efficient outcome.
more »
« less
- Award ID(s):
- 1824317
- NSF-PAR ID:
- 10099969
- Date Published:
- Journal Name:
- EC '19 Proceedings of the 2019 ACM Conference on Economics and Computation
- Page Range / eLocation ID:
- 581 to 582
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Electric scooters (or e-scooters) are among the most popular micromobility options that have experienced an enormous expansion in urban transportation systems across the world in recent years. Along with the increased usage of e-scooters, the increasing number of e-scooter-related injuries has also become an emerging global public health concern. However, little is known regarding the risk factors for e-scooter-related crashes and injury crashes. This study consisted of a two-phase survey questionnaire administered to a cohort of e-scooter riders (n = 210), which obtained exposure information on riders’ demographics, riding behaviors (including infrastructure selection), helmet use, and other crash-related factors. The risk ratios of riders’ self-reported involvement in an e-scooter-related crash (i.e., any crash versus no crash) and injury crash (i.e., injury crash versus non-injury crash) were estimated across exposure subcategories using the Negative Binomial regression approach. Males and frequent users of e-scooters were associated with an increased risk of e-scooter-related crashes of any type. For the e-scooter-related injury crashes, more frequently riding on bike lanes (i.e., greater than 25% of the time), either protected or unprotected, was identified as a protective factor. E-scooter-related injury crashes were more likely to occur among females, who reported riding on sidewalks and non-paved surfaces more frequently. The study may help inform public policy regarding e-scooter legislation and prioritize efforts to establish suitable road infrastructure for improved e-scooter riding safety.more » « less
-
more » « less
Abstract We explore efficiency and optimal policy in decentralized transport markets, such as taxis, trucks, and bulk shipping. We show that in these markets, search frictions distort the transportation network and the dynamic allocation of carriers over space. We derive explicit and intuitive conditions for efficiency and show how they translate into efficient pricing rules, or optimal taxes and subsidies for the planner who cannot set prices directly. The results imply that destination-based pricing is essential to attain efficiency. Then, using data from dry bulk shipping, we demonstrate that search frictions lead to a sizable social loss and substantial misallocation of ships over space. Optimal policy can eliminate about half of the welfare loss. Can a centralizing platform, often arising as a market-based solution to search frictions, do better? Interestingly, the answer is no; although the platform eradicates frictions, it exerts market power, thus eroding the welfare gains. Finally, we use two recent interventions in the industry (China’s Belt and Road Initiative and the environmental initiative IMO 2020) to demonstrate that taking into account the efficiency properties of transport markets is germane to any proposed policy.
-
Already known as densely populated areas with land use including housing, transportation, sanitation, utilities and communication, nowadays, cities tend to grow even bigger. Genuine road-user's types are emerging with further technological developments to come. As cities population size escalates, and roads getting congested, government agencies such as Department of Transportation (DOT) through the National Highway Traffic Safety Administration (NHTSA) are in pressing need to perfect their management systems with new efficient technologies. The challenge is to anticipate on never before seen problems, in their effort to save lives and implement sustainable cost-effective management systems. To make things yet more complicated and a bit daunting, self-driving car will be authorized in a close future in crowded major cities where roads are to be shared among pedestrians, cyclists, cars, and trucks. Roads sizes and traffic signaling will need to be constantly adapted accordingly. Counting and classifying turning vehicles and pedestrians at an intersection is an exhausting task and despite traffic monitoring systems use, human interaction is heavily required for counting. Our approach to resolve traffic intersection turning-vehicles counting is less invasive, requires no road dig up or costly installation. Live or recorded videos from already installed camera all over the cities can be used as well as any camera including cellphones. Our system is based on Neural Network and Deep Learning of object detection along computer vision technology and several methods and algorithms. Our approach will work on still images, recorded-videos, real-time live videos and will detect, classify, track and compute moving object velocity and direction using convolution neural network. Created based upon series of algorithms modeled after the human brain, our system uses NVIDIA Video cards with GPU, CUDA, OPENCV and mathematical vectors systems to perform.more » « less
-
Connected Autonomous Vehicles (CAVs) are expected to enable reliable, efficient, and intelligent transportation systems. Most motion planning algorithms for multi-agent systems implicitly assume that all vehicles/agents will execute the expected plan with a small error and evaluate their safety constraints based on this fact. This assumption, however, is hard to keep for CAVs since they may have to change their plan (e.g., to yield to another vehicle) or are forced to stop (e.g., A CAV may break down). While it is desired that a CAV never gets involved in an accident, it may be hit by other vehicles and sometimes, preventing the accident is impossible (e.g., getting hit from behind while waiting behind the red light). Responsibility-Sensitive Safety (RSS) is a set of safety rules that defines the objective of CAV to blame, instead of safety. Thus, instead of developing a CAV algorithm that will avoid any accident, it ensures that the ego vehicle will not be blamed for any accident it is a part of. Original RSS rules, however, are hard to evaluate for merge, intersection, and unstructured road scenarios, plus RSS rules do not prevent deadlock situations among vehicles. In this paper, we propose a new formulation for RSS rules that can be applied to any driving scenario. We integrate the proposed RSS rules with the CAV’s motion planning algorithm to enable cooperative driving of CAVs. We use Control Barrier Functions to enforce safety constraints and compute the energy optimal trajectory for the ego CAV. Finally, to ensure liveness, our approach detects and resolves deadlocks in a decentralized manner. We have conducted different experiments to verify that the ego CAV does not cause an accident no matter when other CAVs slow down or stop. We also showcase our deadlock detection and resolution mechanism using our simulator. Finally, we compare the average velocity and fuel consumption of vehicles when they drive autonomously with the case that they are autonomous and connected.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1145/3328526.3329625
