{rfName}
Mo

Indexed in

License and use

Citations

9

Altmetrics

Analysis of institutional authors

Paniego SCorresponding AuthorCanas J.Author
Share
Publications
>
Article

Model Optimization in Deep Learning Based Robot Control for Autonomous Driving

Publicated to:Ieee Robotics And Automation Letters. 9 (1): 715-722 - 2024-01-01 9(1), DOI: 10.1109/LRA.2023.3336244

Authors: Paniego, Sergio; Paliwal, Nikhil; Canas, Jose Maria

Affiliations

JdeRobot Org, Madrid 28922, Spain - Author
JdeRobot Organization, Madrid, 28922, Spain - Author
JdeRobot Organization, Madrid, 28922, Spain, Saarland University, Saarbrücken, 66123, Germany - Author
Saarland Univ, D-66123 Saarbrucken, Germany - Author
Saarland University, Saarbrücken, 66123, Germany - Author
Univ Rey Juan Carlos, Madrid 28933, Spain - Author
Universidad Rey Juan Carlos, Madrid, 28933, Spain - Author
Universidad Rey Juan Carlos, Madrid, 28933, Spain, JdeRobot Organization, Madrid, 28922, Spain - Author
See more

Abstract

Deep learning (DL) has been successfully used in robotics for perception tasks and end-to-end robot control. In the context of autonomous driving, this work explores and compares a variety of alternatives for model optimization to solve the visual lane-follow application in urban scenarios with an imitation learning approach. The optimization techniques include quantization, pruning, fine-tuning (retraining), and clustering, covering all the options available at the most common DL frameworks. TensorRT optimization for specific cutting-edge hardware devices has been also explored. For the comparison, offline metrics such as mean squared error and inference time are used. In addition, the optimized models have been evaluated in an online fashion using the autonomous driving state-of-the-art simulator CARLA and an assessment tool called Behavior Metrics, which provides holistic quantitative fine-grain data about robot performance. Typically the performance of robot applications depends both on the quality of the control decisions and also on their frequency. The studied optimized models significantly increase inference frequency without losing decision quality. The impact of each optimization alone has also been measured. This speed-up allows us to successfully run DL robot-control applications even in limited computing hardware. All the work presented here is open-source, including models, weights, assessment tool, and dataset, for easy replication and extension. © 2016 IEEE.

Keywords
machine learning for robot controlsensorimotor learningAutonomous vehiclesDeep learningImitation learningIndustrial robotsMachine learning for robot controlMachine-learningMean square errorOpen systemsOptimisationsQuality controlRobot applicationsRobot sensing systemRobots controlSensorimotor learningSensorimotors

Quality index

Bibliometric impact. Analysis of the contribution and dissemination channel

The work has been published in the journal Ieee Robotics And Automation Letters due to its progression and the good impact it has achieved in recent years, according to the agency Scopus (SJR), it has become a reference in its field. In the year of publication of the work, 2024 there are still no calculated indicators, but in 2023, it was in position , thus managing to position itself as a Q1 (Primer Cuartil), in the category Control and Optimization. Notably, the journal is positioned above the 90th percentile.

From a relative perspective, and based on the normalized impact indicator calculated from the Field Citation Ratio (FCR) of the Dimensions source, it yields a value of: 3.54, which indicates that, compared to works in the same discipline and in the same year of publication, it ranks as a work cited above average. (source consulted: Dimensions May 2025)

Specifically, and according to different indexing agencies, this work has accumulated citations as of 2025-05-10, the following number of citations:

  • WoS: 4
  • Scopus: 5
  • OpenCitations: 5
Impact and social visibility

From the perspective of influence or social adoption, and based on metrics associated with mentions and interactions provided by agencies specializing in calculating the so-called "Alternative or Social Metrics," we can highlight as of 2025-05-10:

  • The use, from an academic perspective evidenced by the Altmetric agency indicator referring to aggregations made by the personal bibliographic manager Mendeley, gives us a total of: 15.
  • The use of this contribution in bookmarks, code forks, additions to favorite lists for recurrent reading, as well as general views, indicates that someone is using the publication as a basis for their current work. This may be a notable indicator of future more formal and academic citations. This claim is supported by the result of the "Capture" indicator, which yields a total of: 15 (PlumX).

With a more dissemination-oriented intent and targeting more general audiences, we can observe other more global scores such as:

  • The Total Score from Altmetric: 2.5.
  • The number of mentions on the social network X (formerly Twitter): 3 (Altmetric).
Leadership analysis of institutional authors

This work has been carried out with international collaboration, specifically with researchers from: Germany.

There is a significant leadership presence as some of the institution’s authors appear as the first or last signer, detailed as follows: First Author (Paniego Blanco, Sergio) and Last Author (Cañas Plaza, Jose María).

the author responsible for correspondence tasks has been Paniego Blanco, Sergio.