Real-time control for at-limit handling driving on a predefined path

Novi, Tommaso; Liniger, Alexander; Capitani, Renzo; Annicchiarico, Claudio

doi:10.1080/00423114.2019.1605081

Cited by 41 publications

(33 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, in this work, we show that co-designing the lowlevel controller to work in harmony with the higher levels allows to drastically improve the performance of the autonomous racecar. This reinforces recent work which showed that better coupling the track and mid-level controllers [10], [17] can improve the performance, and [18] that highlighted the benefits of torque vectoring for autonomous cars.…”

Section: Introductionsupporting

confidence: 88%

“…Several papers discovered model mismatch as a crucial issue in autonomous racing -the problem arises due to the relatively simple models used in most autonomous racing stacks. Solutions range from using complex models [17], stochastic MPC [19], to NMPC with model learning [20], [21] to learn the model mismatch. All these methods tackle the problem in the mid-level and come with drawbacks in terms of the computational load.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Holistic Motion Planning and Control Solution to Challenge a Professional Racecar Driver

Srinivasan,

Giles,

Liniger

2021

Preprint

View full text Add to dashboard Cite

We present a holistically designed three layer control architecture capable of outperforming a professional driver racing the same car. Our approach focuses on the codesign of the motion planning and control layers, extracting the full potential of the connected system. First, a high-level planner computes an optimal trajectory around the track, then in real-time the mid-level nonlinear model predictive controller follows this path using the high-level information as guidance. Finally a high frequency, low-level controller tracks the states predicted by the mid-level controller. Tracking the predicted behavior has two advantages: it reduces the mismatch between the model used in the upper layers and the real car, and allows for a torque vectoring command to be optimized by the higher level motion planners. The tailored design of the low-level controller proved to be crucial for bridging the gap between planning and control, unlocking unseen performance in autonomous racing. The proposed approach was verified on a full size racecar, resulting in a considerable improvement over the state-of-the-art results achieved on the same vehicle. Finally, we also show that the proposed co-design approach outperforms a professional racecar driver.

show abstract

Section: Introductionsupporting

confidence: 88%

Section: Introductionmentioning

confidence: 99%

A Holistic Motion Planning and Control Solution to Challenge a Professional Racecar Driver

Srinivasan,

Giles,

Liniger

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Classical Approaches Classical approaches to autonomous car racing approach the problem by separating it in a chain of submodules consisting of perception, trajectory planning, and control. In particular, model predictive control (MPC) [2], [11]- [15] is a promising approach for controlling the vehicle at high speed. In [16], an MPC controller is combined with learned system dynamics based on Gaussian Processes for the task of autonomous car racing.…”

Section: Related Workmentioning

confidence: 99%

Super-Human Performance in Gran Turismo Sport Using Deep Reinforcement Learning

Fuchs¹,

Song

Kaufmann

et al. 2021

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Autonomous car racing is a major challenge in robotics. It raises fundamental problems for classical approaches such as planning minimum-time trajectories under uncertain dynamics and controlling the car at the limits of its handling. Besides, the requirement of minimizing the lap time, which is a sparse objective, and the difficulty of collecting training data from human experts have also hindered researchers from directly applying learning-based approaches to solve the problem. In the present work, we propose a learning-based system for autonomous car racing by leveraging a high-fidelity physical car simulation, a course-progress proxy reward, and deep reinforcement learning. We deploy our system in Gran Turismo Sport, a world-leading car simulator known for its realistic physics simulation of different race cars and tracks, which is even used to recruit human race car drivers. Our trained policy achieves autonomous racing performance that goes beyond what had been achieved so far by the built-in AI, and at the same time, outperforms the fastest driver in a dataset of over 50,000 human players.

show abstract

“…This deceleration is conservative for such a racecar as shown in Figure 31b. Note that if shorter horizons are desired, methods that guarantee recursive feasibility using terminal constraints (Liniger & Lygeros, 2019; Rosolia et al, 2017) can be used, or methods using smart terminal velocity constraints (Novi, Liniger, Capitani, & Annicchiarico, 2019). The predicted horizon of the MPC with corresponding track constraints can be seen in Figure 29a.…”

Section: Controlmentioning

confidence: 99%

AMZ Driverless: The full autonomous racing system

Kabzan

Valls

Reijgwart

et al. 2020

Journal of Field Robotics

106

View full text Add to dashboard Cite

This paper presents the algorithms and system architecture of an autonomous racecar. The introduced vehicle is powered by a software stack designed for robustness, reliability, and extensibility. To autonomously race around a previously unknown track, the proposed solution combines state of the art techniques from different fields of robotics. Specifically, perception, estimation, and control are incorporated into one high‐performance autonomous racecar. This complex robotic system, developed by AMZ Driverless and ETH Zürich, finished first overall at each competition we attended: Formula Student Germany 2017, Formula Student Italy 2018 and Formula Student Germany 2018. We discuss the findings and learnings from these competitions and present an experimental evaluation of each module of our solution.

show abstract

Real-time control for at-limit handling driving on a predefined path

Cited by 41 publications

References 25 publications

A Holistic Motion Planning and Control Solution to Challenge a Professional Racecar Driver

A Holistic Motion Planning and Control Solution to Challenge a Professional Racecar Driver

Super-Human Performance in Gran Turismo Sport Using Deep Reinforcement Learning

AMZ Driverless: The full autonomous racing system

Contact Info

Product

Resources

About