The Effects of Speed and Delays on Test-Time Performance of End-to-End Self-Driving
This study investigates the effects of speed variations and computational delays on the performance of end-to-end autonomous driving systems (ADS). Utilizing 1:10 scale mini-cars with limited computational resources, we demonstrate that different driving speeds significantly alter the task of the dr...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/6/1963 |
| _version_ | 1827304970144186368 |
|---|---|
| author | Ardi Tampuu Kristjan Roosild Ilmar Uduste |
| author_facet | Ardi Tampuu Kristjan Roosild Ilmar Uduste |
| author_sort | Ardi Tampuu |
| collection | DOAJ |
| description | This study investigates the effects of speed variations and computational delays on the performance of end-to-end autonomous driving systems (ADS). Utilizing 1:10 scale mini-cars with limited computational resources, we demonstrate that different driving speeds significantly alter the task of the driving model, challenging the generalization capabilities of systems trained at a singular speed profile. Our findings reveal that models trained to drive at high speeds struggle with slower speeds and vice versa. Consequently, testing an ADS at an inappropriate speed can lead to misjudgments about its competence. Additionally, we explore the impact of computational delays, common in real-world deployments, on driving performance. We present a novel approach to counteract the effects of delays by adjusting the target labels in the training data, demonstrating improved resilience in models to handle computational delays effectively. This method, crucially, addresses the effects of delays rather than their causes and complements traditional delay minimization strategies. These insights are valuable for developing robust autonomous driving systems capable of adapting to varying speeds and delays in real-world scenarios. |
| first_indexed | 2024-04-24T17:49:15Z |
| format | Article |
| id | doaj.art-44fd9e6cb34b4c70beb70fc1047745f0 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-24T17:49:15Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-44fd9e6cb34b4c70beb70fc1047745f02024-03-27T14:04:15ZengMDPI AGSensors1424-82202024-03-01246196310.3390/s24061963The Effects of Speed and Delays on Test-Time Performance of End-to-End Self-DrivingArdi Tampuu0Kristjan Roosild1Ilmar Uduste2Insititute of Computer Science, University of Tartu, 51009 Tartu, EstoniaInsititute of Computer Science, University of Tartu, 51009 Tartu, EstoniaInsititute of Computer Science, University of Tartu, 51009 Tartu, EstoniaThis study investigates the effects of speed variations and computational delays on the performance of end-to-end autonomous driving systems (ADS). Utilizing 1:10 scale mini-cars with limited computational resources, we demonstrate that different driving speeds significantly alter the task of the driving model, challenging the generalization capabilities of systems trained at a singular speed profile. Our findings reveal that models trained to drive at high speeds struggle with slower speeds and vice versa. Consequently, testing an ADS at an inappropriate speed can lead to misjudgments about its competence. Additionally, we explore the impact of computational delays, common in real-world deployments, on driving performance. We present a novel approach to counteract the effects of delays by adjusting the target labels in the training data, demonstrating improved resilience in models to handle computational delays effectively. This method, crucially, addresses the effects of delays rather than their causes and complements traditional delay minimization strategies. These insights are valuable for developing robust autonomous driving systems capable of adapting to varying speeds and delays in real-world scenarios.https://www.mdpi.com/1424-8220/24/6/1963end-to-end drivingdelaysout of distributionADS testing |
| spellingShingle | Ardi Tampuu Kristjan Roosild Ilmar Uduste The Effects of Speed and Delays on Test-Time Performance of End-to-End Self-Driving Sensors end-to-end driving delays out of distribution ADS testing |
| title | The Effects of Speed and Delays on Test-Time Performance of End-to-End Self-Driving |
| title_full | The Effects of Speed and Delays on Test-Time Performance of End-to-End Self-Driving |
| title_fullStr | The Effects of Speed and Delays on Test-Time Performance of End-to-End Self-Driving |
| title_full_unstemmed | The Effects of Speed and Delays on Test-Time Performance of End-to-End Self-Driving |
| title_short | The Effects of Speed and Delays on Test-Time Performance of End-to-End Self-Driving |
| title_sort | effects of speed and delays on test time performance of end to end self driving |
| topic | end-to-end driving delays out of distribution ADS testing |
| url | https://www.mdpi.com/1424-8220/24/6/1963 |
| work_keys_str_mv | AT arditampuu theeffectsofspeedanddelaysontesttimeperformanceofendtoendselfdriving AT kristjanroosild theeffectsofspeedanddelaysontesttimeperformanceofendtoendselfdriving AT ilmaruduste theeffectsofspeedanddelaysontesttimeperformanceofendtoendselfdriving AT arditampuu effectsofspeedanddelaysontesttimeperformanceofendtoendselfdriving AT kristjanroosild effectsofspeedanddelaysontesttimeperformanceofendtoendselfdriving AT ilmaruduste effectsofspeedanddelaysontesttimeperformanceofendtoendselfdriving |