2019 IEEE International Conference on Embedded Software and Systems (ICESS) 2019
DOI: 10.1109/icess.2019.8782446
|View full text |Cite
|
Sign up to set email alerts
|

Towards Heterogeneous Computing Platforms for Autonomous Driving

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
9
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 18 publications
(9 citation statements)
references
References 14 publications
0
9
0
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%
“…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%
“…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%
“…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%