An Automated Learning-Based Procedure for Large-scale Vehicle Dynamics Modeling on Baidu Apollo Platform

Xu, Jiaxuan; Luo, Qi; Xu, Kecheng; Xiao, Xiangquan; Yu, Siyang; Hu, Jiangtao; Miao, Jinghao; Wang, Jingao

doi:10.1109/iros40897.2019.8968102

Cited by 33 publications

(17 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[6]. Figure 2 shows the main functions of ADS according Autoware 1 [23], [24], Apollo 2 [25] and Elektrobit open robinos 3 [26].…”

Section: Ads and Adasmentioning

confidence: 99%

Finding Critical Scenarios for Automated Driving Systems: A Systematic Literature Review

Zhang¹,

Tao²,

Tan³

et al. 2021

Preprint

View full text Add to dashboard Cite

Scenario-based approaches have been receiving a huge amount of attention in research and engineering of automated driving systems. Due to the complexity and uncertainty of the driving environment, and the complexity of the driving task itself, the number of possible driving scenarios that an ADS or ADAS may encounter is virtually infinite. Therefore it is essential to be able to reason about the identification of scenarios and in particular critical ones that may impose unacceptable risk if not considered. Critical scenarios are particularly important to support design, verification and validation efforts, and as a basis for a safety case. In this paper, we present the results of a systematic literature review in the context of autonomous driving. The main contributions are: (i) introducing a comprehensive taxonomy for critical scenario identification methods; (ii) giving an overview of the state-of-the-art research based on the taxonomy encompassing 86 papers between 2017 and 2020; and (iii) identifying open issues and directions for further research. The provided taxonomy comprises three main perspectives encompassing the problem definition (the why), the solution (the methods to derive scenarios), and the assessment of the established scenarios. In addition, we discuss open research issues considering the perspectives of coverage, practicability, and scenario space explosion.

show abstract

“…[6]. Figure 2 shows the main functions of ADS according Autoware 1 [23], [24], Apollo 2 [25] and Elektrobit open robinos 3 [26].…”

Section: Ads and Adasmentioning

confidence: 99%

Finding Critical Scenarios for Automated Driving Systems: A Systematic Literature Review

Zhang¹,

Tao²,

Tan³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Training Pipeline Verification Either manual driving data or autonomous driving data (as long as the throttle/brake/steering behaves the same under control commands) can be taken as training data. In order to make training data evenly distributed in input (control command) and output (vehicle state) spaces, the same feature collection and extraction standard is applied as described in our previous work [17]. Here we choose a pre-trained MLP model [17], which passes a 5-dimensional input to an 8-dimensional fully-connected layer with ReLU activation and produces a 2-dimensional output.…”

Section: Data Acquisitonmentioning

confidence: 99%

“…In order to make training data evenly distributed in input (control command) and output (vehicle state) spaces, the same feature collection and extraction standard is applied as described in our previous work [17]. Here we choose a pre-trained MLP model [17], which passes a 5-dimensional input to an 8-dimensional fully-connected layer with ReLU activation and produces a 2-dimensional output. As shown in Fig.…”

Section: Data Acquisitonmentioning

confidence: 99%

“…In some more recent work [16], Deep NN involving Convolutional NN (CNN) and Multi-Layer Perceptron (MLP) were trained to compute vehicle controls; however, the classic state-space vehicle models were still employed and hence, the potential improvement the deep learning may bring in was limited. Further, our Baidu Apollo team has proposed a learning-based dynamic modeling method [17], in which the NN methods were leveraged to model the complicated vehicle dynamics. It has higher accuracy and lower cost compared to the rule-based model and is suitable for large-scale autonomous driving system deployment.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

DRF: A Framework for High-Accuracy Autonomous Driving Vehicle Modeling

Jiang,

Wang,

Lin

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

An accurate vehicle dynamic model is the key to bridge the gap between simulation and real road test in autonomous driving. In this paper, we present a Dynamic model-Residual correction model Framework (DRF) for vehicle dynamic modeling. On top of any existing open-loop dynamic model, this framework builds a Residual Correction Model (RCM) by integrating deep Neural Networks (NN) with Sparse Variational Gaussian Process (SVGP) model. RCM takes a sequence of vehicle control commands and dynamic status for a certain time duration as modeling inputs, extracts underlying context from this sequence with deep encoder networks, and predicts open-loop dynamic model prediction errors. Five vehicle dynamic models are derived from DRF via encoder variation. Our contribution is consolidated by experiments on evaluation of absolute trajectory error and similarity between DRF outputs and the ground truth. Compared to classic rule-based and learning-based vehicle dynamic models, DRF accomplishes as high as 74.12% to 85.02% of absolute trajectory error drop among all DRF variations.

show abstract

“…Inspired by H-OBCA, we present Temporal and Dual warm starts with Reformulated Optimization-based Collision Avoidance (TDR-OBCA) algorithm with improved robustness, driving comfort and efficiency, and integrate it with Apollo Autonomous Driving Platform [13]. Our contributions are: [14] with powerful solvers specially for MPC, such as GRAMPC [15].…”

Section: Introductionmentioning

confidence: 99%

TDR-OBCA: A Reliable Planner for Autonomous Driving in Free-Space Environment

He¹,

Zhou²,

Jiang³

et al. 2021

2021 American Control Conference (ACC)

Self Cite

View full text Add to dashboard Cite

This paper presents an optimization-based collision avoidance trajectory generation method for autonomous driving in free-space environments, with enhanced robustness, driving comfort and efficiency. Starting from the hybrid optimization-based framework, we introduces two warm start methods, temporal and dual variable warm starts, to improve the efficiency. We also reformulates the problem to improve the robustness and efficiency. We name this new algorithm TDR-OBCA. With these changes, compared with original hybrid optimization we achieve a 96.67% failure rate decrease with respect to initial conditions, 13.53% increase in driving comforts and 3.33% to 44.82% increase in planner efficiency as obstacles number scales. We validate our results in hundreds of simulation scenarios and hundreds of hours of public road tests in both U.S. and China. Our source code is available at https://github.com/ApolloAuto/apollo.

show abstract

An Automated Learning-Based Procedure for Large-scale Vehicle Dynamics Modeling on Baidu Apollo Platform

Cited by 33 publications

References 11 publications

Finding Critical Scenarios for Automated Driving Systems: A Systematic Literature Review

Finding Critical Scenarios for Automated Driving Systems: A Systematic Literature Review

DRF: A Framework for High-Accuracy Autonomous Driving Vehicle Modeling

TDR-OBCA: A Reliable Planner for Autonomous Driving in Free-Space Environment

Contact Info

Product

Resources

About