Towards Heterogeneous Computing Platforms for Autonomous Driving

Chishiro, Hiroyuki; Kazutoshi, Suito; Ito, Tsutomu; Maeda, Seiya; Azumi, Takuya; Funaoka, Kenji; Kato, Shigeo

doi:10.1109/icess.2019.8782446

Cited by 18 publications

(9 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [19], the authors present an edge-cloud computing model for autonomous vehicles using the open-source software platform Autoware [20]. They believe that their proposed edge-cloud computing model for Autoware-based autonomous vehicles reduces the execution time and the total deadline miss.…”

Section: A Autonomous Vehicles and Edge Computing Convergencementioning

confidence: 99%

Next-Generation Edge Computing Assisted Autonomous Driving Based Artificial Intelligence Algorithms

et al. 2022

View full text Add to dashboard Cite

Edge Computing and Network Function Virtualization (NFV) concepts can improve network processing and multi-resources allocation when intelligent optimization algorithms are deployed. Multiservice offloading and allocation approaches pose interesting challenges in the current and nextgeneration vehicle networks. The state-of-the-art optimization approaches still formulate exact algorithms, and tune approximation methods to get sufficient solutions. These approaches are data-centric that aim to use heterogeneous data inputs to find the near optimal solutions. In the context of connected and autonomous vehicles (CAVs), these techniques show an exponential computational time and deal only with small and medium scale networks. Therefore, we are motivated by using recent Deep Reinforcement Learning (DRL) techniques to learn the behavior of exact optimization algorithms while enhancing the Quality of Service (QoS) of network operators and satisfying the requirements of the next-generation Autonomous Vehicles (AVs). DRL algorithms can improve AVs service offloading and optimize edge resources. An Optimal Virtual Edge Autopilot Placement (OVEAP) algorithm is proposed using Integer Linear Programming (ILP). Moreover, an autopilot placement protocol is presented to support the algorithm. Optimal allocation and Virtual Network Function (VNF) placement and chaining of the autopilot, based on several new constraints such as computing and networking loads, network edge infrastructure, and placement cost, are designed. Further, a DRL approach is formulated to deal with dense Internet of Autonomous Vehicle (IoAV) networks. Extensive simulations and evaluations are carried out. Results show that the proposed allocation strategies outperform the state-of-the-art solutions and give better performance in terms of Total Edge Servers Utilization, Total Edge Servers Allocation Time, and Successfully Allocated autopilots.

show abstract

Section: A Autonomous Vehicles and Edge Computing Convergencementioning

confidence: 99%

Next-Generation Edge Computing Assisted Autonomous Driving Based Artificial Intelligence Algorithms

et al. 2022

View full text Add to dashboard Cite

show abstract

“…AVs are subject to time constraints, since assuring the vehicle always finish the computation within a given time limit is necessary to guarantee safety standards. Some previous works consider a reaction time under 100ms [8], [27], in order to be faster than a high-skilled human reaction. This time constraint poses the AV to be four times faster than the average time humans take to process objects, as studied in [28].…”

Section: B Characterization Proceduresmentioning

confidence: 99%

“…For instance, if Autoware runs with SSD512 (Figure 5a), the vision detection algorithm takes more than 80ms in its mean latency. If we consider a 100ms as the target time constraint for reaction time, as in previous works [8], [27], we are devoting at least 80% of the time only to process the image detection task. When we consider other options such as SSD300 (Figure 5b) and YOLO (Figure 5c), average latency improves, being under 40ms.…”

Section: A Latency Characterizationmentioning

confidence: 99%

Demystifying Power and Performance Bottlenecks in Autonomous Driving Systems

Becker

Arnau

González

2020

2020 IEEE International Symposium on Workload Characterization (IISWC)

View full text Add to dashboard Cite

Autonomous Vehicles (AVs) have the potential to radically change the automotive industry. However, computing solutions for AVs have to meet severe performance and power constraints to guarantee a safe driving experience. Current solutions either exhibit high cost and power dissipation or fail to meet the stringent latency constraints. Therefore, the popularization of AVs requires a low-cost yet effective computing system. Understanding the sources of latency and energy consumption is key in order to improve autonomous driving systems. In this paper, we present a detailed characterization of Autoware, a modern self-driving car system. We analyze the performance and power of the different components and leverage hardware counters to identify the main bottlenecks.Our approach to AV characterization avoids pitfalls of previous works: profiling individual components in isolation and neglecting LiDAR-related components. We base our characterization on a rigorous methodology that considers the entire software stack. Profiling the end-to-end system accounts for interference and contention among different components that run in parallel, also including memory transfers to communicate data. We show that all these factors have a high impact on latency and cannot be measured by profiling isolated modules.Our characterization provides novel insights, some of the interesting findings are the following. First, contention among different modules drastically impacts latency and performance predictability. Second, LiDAR-related components are important contributors to the latency of the system. Finally, a modern platform with a high-end CPU and GPU cannot achieve real-time performance when considering the entire end-to-end system.

show abstract

“…Much progress has been made since the first neural networkdriven car was introduced in 1988 [4] and the execution of three DARPA autonomous car challenges in 2004, 2005, [5], and 2007, [2], [6]. By 2019, for example, Waymo reported to have reached 10 million miles of fully autonomous driving (level 4) [7], whereas Tesla announced to have reached 1 billion miles with its semi-autonomous autopilot (level 2) [8]. Despite these impressive achievements, there is no large scale deployment of AVs yet.…”

Section: Introductionmentioning

confidence: 99%

Deep Reinforcement Learning for Human-Like Driving Policies in Collision Avoidance Tasks of Self-Driving Cars

Emuna¹,

Borowsky²,

Biess³

2020

Preprint

View full text Add to dashboard Cite

The technological and scientific challenges involved in the development of autonomous vehicles (AVs) are currently of primary interest for many automobile companies and research labs. However, human-controlled vehicles are likely to remain on the roads for several decades to come and may share with AVs the traffic environments of the future. In such mixed environments, AVs should deploy human-like driving policies and negotiation skills to enable smooth traffic flow. To generate automated human-like driving policies, we introduce a model-free, deep reinforcement learning approach to imitate an experienced human driver's behavior. We study a static obstacle avoidance task on a two-lane highway road in simulation (Unity). Our control algorithm receives a stochastic feedback signal from two sources: a model-driven part, encoding simple driving rules, such as lanekeeping and speed control, and a stochastic, data-driven part, incorporating human expert knowledge from driving data. To assess the similarity between machine and human driving, we model distributions of track position and speed as Gaussian processes. We demonstrate that our approach leads to humanlike driving policies.

show abstract

Towards Heterogeneous Computing Platforms for Autonomous Driving

Cited by 18 publications

References 14 publications

Next-Generation Edge Computing Assisted Autonomous Driving Based Artificial Intelligence Algorithms

Next-Generation Edge Computing Assisted Autonomous Driving Based Artificial Intelligence Algorithms

Demystifying Power and Performance Bottlenecks in Autonomous Driving Systems

Deep Reinforcement Learning for Human-Like Driving Policies in Collision Avoidance Tasks of Self-Driving Cars

Contact Info

Product

Resources

About