Optimization-Based Autonomous Racing of 1:43 Scale RC Cars
arXiv:1711.07300 · doi:10.1002/oca.2123
Abstract
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.
Cited by in corpus (79)
- Motion Planning for Autonomous Driving: The State of the Art and Future Perspectives
- Cautious Model Predictive Control using Gaussian Process Regression
- Autonomous Vehicles on the Edge: A Survey on Autonomous Vehicle Racing
- Differentiable MPC for End-to-end Planning and Control
- Cautious NMPC with Gaussian Process Dynamics for Autonomous Miniature Race Cars
- Autonomous Drone Racing: A Survey
- Super-Human Performance in Gran Turismo Sport Using Deep Reinforcement Learning
- Time Distributed Optimization for Model Predictive Control: Stability, Robustness, and Constraint Satisfaction
- Analysis and design of model predictive control frameworks for dynamic operation -- An overview
- TUM autonomous motorsport: An autonomous racing software for the Indy Autonomous Challenge
- Real-Time Control for Autonomous Racing Based on Viability Theory
- NMPC trajectory planner for urban autonomous driving
- Autonomous Navigation of MAVs in Unknown Cluttered Environments
- Real-Time Adaptive Velocity Optimization for Autonomous Electric Cars at the Limits of Handling
- Motion Planning and Control for Multi Vehicle Autonomous Racing at High Speeds
- Optimization-Based Collision Avoidance
- Model- and Acceleration-based Pursuit Controller for High-Performance Autonomous Racing
- MPC path-planner for autonomous driving solved by genetic algorithm technique
- A Holistic Motion Planning and Control Solution to Challenge a Professional Racecar Driver
- Contextual Tuning of Model Predictive Control for Autonomous Racing
- Safety-Critical Model Predictive Control with Discrete-Time Control Barrier Function
- Guaranteeing Consistency in a Motion Planning and Control Architecture Using a Kinematic Bicycle Model
- Networked and Autonomous Model-scale Vehicles for Experiments in Research and Education
- Search-Based Task and Motion Planning for Hybrid Systems: Agile Autonomous Vehicles
- Chronos and CRS: Design of a miniature car-like robot and a software framework for single and multi-agent robotics and control
- Autonomous Drone Racing with Deep Reinforcement Learning
- DDK: A Deep Koopman Approach for Dynamics Modeling and Trajectory Tracking of Autonomous Vehicles
- Game-Theoretic Model Predictive Control with Data-Driven Identification of Vehicle Model for Head-to-Head Autonomous Racing
- A Nonlinear Model Predictive Control Strategy for Autonomous Racing of Scale Vehicles
- Autonomous Driving Small-Scale Cars: A Survey of Recent Development
- A Learning-based Nonlinear Model Predictive Controller for a Real Go-Kart based on Black-box Dynamics Modeling through Gaussian Processes
- Sampling-Based Motion Planning with Online Racing Line Generation for Autonomous Driving on Three-Dimensional Race Tracks
- Learning-Based On-Track System Identification for Scaled Autonomous Racing in Under a Minute
- Low-complexity method for hybrid MPC with local guarantees
- TC-Driver: Trajectory Conditioned Driving for Robust Autonomous Racing -- A Reinforcement Learning Approach
- CODEI: Resource-Efficient Task-Driven Co-Design of Perception and Decision Making for Mobile Robots Applied to Autonomous Vehicles
- Online Constrained Model-based Reinforcement Learning
- Competitive Driving of Autonomous Vehicles
- Winning the 3rd Japan Automotive AI Challenge -- Autonomous Racing with the Autoware.Auto Open Source Software Stack
- CMPCC: Corridor-based Model Predictive Contouring Control for Aggressive Drone Flight
- BayesRace: Learning to race autonomously using prior experience
- Real-Time Predictive Control for Precision Machining
- Automating Vehicles by Deep Reinforcement Learning using Task Separation with Hill Climbing
- An Optimal Control Approach to Sequential Machine Teaching
- Structured learning of safety guarantees for the control of uncertain dynamical systems
- Predictive Spliner: Data-Driven Overtaking in Autonomous Racing Using Opponent Trajectory Prediction
- Enhancing State Estimator for Autonomous Racing : Leveraging Multi-modal System and Managing Computing Resources
- Safe and Near-Optimal Policy Learning for Model Predictive Control using Primal-Dual Neural Networks
- Local NMPC on Global Optimised Path for Autonomous Racing
- Vision-Based Autonomous Car Racing Using Deep Imitative Reinforcement Learning
- Learning to Race through Coordinate Descent Bayesian Optimisation
- Safe Autonomous Racing via Approximate Reachability on Ego-vision
- Non-Linear Model Predictive Control with Adaptive Time-Mesh Refinement
- Hierarchical Time-Optimal Planning for Multi-Vehicle Racing
- Architecting Dependable Learning-enabled Autonomous Systems: A Survey
- EVA-Planner: Environmental Adaptive Quadrotor Planning
- Factor Graph-Based Planning as Inference for Autonomous Vehicle Racing
- Off the Beaten Track: Laterally Weighted Motion Planning for Local Obstacle Avoidance
- The Mini Wheelbot: A Testbed for Learning-based Balancing, Flips, and Articulated Driving
- Track based Offline Policy Learning for Overtaking Maneuvers with Autonomous Racecars
- A Dual-level Model Predictive Control Scheme for Multi-timescale Dynamical Systems--Extended Version
- Traction Adaptive Motion Planning at the Limits of Handling
- Competitive Policy Optimization
- Performance-driven Constrained Optimal Auto-Tuner for MPC
- MATS: An Interpretable Trajectory Forecasting Representation for Planning and Control
- Reduce Lap Time for Autonomous Racing with Curvature-Integrated MPCC Local Trajectory Planning Method
- Adaptive Lookahead Pure-Pursuit for Autonomous Racing
- Online Reachability Analysis and Space Convexification for Autonomous Racing
- A Receding Horizon Approach for Simultaneous Active Learning and Control using Gaussian Processes
- Does Unpredictability Influence Driving Behavior?
- A predictive safety filter for learning-based racing control
- Trajectory Planning for an Articulated Commercial Vehicle using Model Predictive Contouring Control
- Hybrid Energy-Aware Reward Shaping: A Unified Lightweight Physics-Guided Methodology for Policy Optimization
- Kernel-Based Metrics Learning for Uncertain Opponent Vehicle Trajectory Prediction in Autonomous Racing
- GPU-Accelerated Barrier-Rate Guided MPPI Control for Tractor-Trailer Systems
- A Simple Approach to Constraint-Aware Imitation Learning with Application to Autonomous Racing
- Fast and Real-time End to End Control in Autonomous Racing Cars Through Representation Learning
- Gaussian Process-Based Model Predictive Control for Overtaking
- High-Speed Trajectory Planning for Autonomous Vehicles Using a Simple Dynamic Model