Optimization‐based autonomous racing of 1:43 scale RC cars

By Alexander Liniger, Alexander Domahidi, Manfred Morari. arXiv.org, 2015

576 citations recorded by the source corpus.

This paper describes autonomous racing of RC race cars based on mathematical optimization. Using a dynamical model of the vehicle, control inputs are computed by receding horizon based controllers, where the objective is to maximize progress on the track subject to the requirement of staying on the track and avoiding opponents. Two different control formulations are presented. The first controller employs a two‐level structure, consisting of a path planner and a nonlinear model predictive controller (NMPC) for tracking. The second controller combines both tasks in one nonlinear optimization problem (NLP) following the ideas of contouring control. Linear time varying models obtained by linearization are used to build local approximations of the control NLPs in the form of convex quadratic programs (QPs) at each sampling time. The resulting QPs have a typical MPC structure and can be solved in the range of milliseconds by recent structure exploiting solvers, which is key to the real‐time feasibility of the overall control scheme. Obstacle avoidance is incorporated by means of a high‐level corridor planner based on dynamic programming, which generates convex constraints for the controllers according to the current position of opponents and the track layout. The control performance is investigated experimentally using 1:43 scale RC race cars, driven at speeds of more than 3 m/s and in operating regions with saturated rear tire forces (drifting). The algorithms run at 50 Hz sampling rate on embedded computing platforms, demonstrating the real‐time feasibility and high performance of optimization‐based approaches for autonomous racing. Copyright © 2014 John Wiley & Sons, Ltd.

Subfields: Automotive Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/1f3486989c79a527dac35324e17df4596146a07a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Automotive Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Learning-Based Model Predictive Control for Autonomous Racing (2019, methodology): “companies and researchers make use of Model Predictive Control (MPC) for path following and racing of autonomous vehicles [4]–[6].”
Collision Avoidance and Stabilization for Autonomous Vehicles in Emergency Scenarios (2017, background): “[10] demonstrated time optimal trajectory generation and tracking around a race track with other vehicles, without explicit stabilization constraints, for remote control vehicle racing.”
A Survey of State-Action Representations for Autonomous Driving (2018, background): “Liniger et al. (2014); Song et al. (2016); Wray et al. (2017) use it as static reference information that de(cid:28)nes constraints on the state-space, such as forbidden error states.”
Optimization-Based Collision Avoidance (2017, methodology): “Optimization-based trajectory planning algorithms such as Model Predictive Control (MPC) have received signiﬁcant attention recently, ranging from (unmanned) aircraft to robots to autonomous cars [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12].”
Information-Theoretic Model Predictive Control: Theory and Applications to Autonomous Driving (2017, background): “Both of these approaches could be applied to the task of autonomous racing (beyond following a prespecified path), and this is an increasingly active research area [18]–[20].”
GPT-Driver: Learning to Drive with GPT (2023, background): “In contrast, the learning-based approaches Bojarski et al. (2016) Hu et al. (2022; 2023); Dauner et al. (2023) proposed to handle complex driving scenarios by learning from large-scale human driving data.”
An Optimal Control Approach to Sequential Machine Teaching (2018, methodology): “Such an approach is used in Liniger et al. (2015), for example, to design controllers for autonomous race cars, and would be an interesting avenue of future work for the machine teaching problem.”
Cautious Model Predictive Control Using Gaussian Process Regression (2017, methodology): “Details on the state estimation can be found in [32].”
Autonomous Vehicles on the Edge: A Survey on Autonomous Vehicle Racing (2022, background): “As a result the researchers displayed new developments in the field of MPC [37], [86], [117]–[120], game theory [122] and reinforcement learning [40].”
Differentiable MPC for End-to-end Planning and Control (2018, methodology): “Many model-based approaches utilize Model Predictive Control (MPC) to perform complex control tasks [González et al., 2011, Lenz et al., 2015, Liniger et al., 2014, Kamel et al., 2015, Erez et al., 2012, Alexis et al., 2011, Bouffard et al., 2012, Neunert et al., 2016].”
Trajectory-Tracking Control of Mobile Robot Systems Incorporating Neural-Dynamic Optimized Model Predictive Approach (2016, methodology): “In [43], an approach called fast optimization for real-time control on embedded system (FORCES) was utilized to compute the control inputs for autonomous racing cars, where linear time varying models were obtained to build local approximations of nonlinear optimization in the form of convex quadrati”
Motion Planning for Autonomous Driving: The State of the Art and Future Perspectives (2023, methodology): “An optimization-based method discretizes the original OCP into a mathematical program (MP), the solution of which are high-resolution state grids [24], [25].”
HPIPM: a high-performance quadratic programming framework for model predictive control (2020, background): “At the time of writing, HPIPM is employed as a QP solver in several NLP solvers such as acados (Verschueren et al., 2019), Control Toolbox (Giftthaler et al., 2018), MPCC (Liniger et al., 2015) and MATMPC (Chen et al., 2018).”