The Idea
The Autonomous Challenge at CES 2022 (AC@CES) is the next big challenge in autonomous racing after the Indy Autonomous Challenge (IAC) . The goal is to demonstrate in a competitive environment the current state of research in autonomous driving on the race track. As one of the largest trade shows in the global tech industry, CES provides the appropriate stage for such a race. The final competition will take place on January 07, 2022 at the Las Vegas Motor Speedway - the event will be broadcasted live on the Indy Autonomous Challenge (IAC) website. The format will be a high-speed passing competition, for which all parts of the AV software from perception to prediction and planning to control must be developed.
The Goal
Our team, TUM Autonomous Motorsport, enters the race as defending champions and wants to fight for the title again. The ultimate goal is to improve our existing software at the driving dynamic limit in competition with other objects and to demonstrate the potential of the software on the race track. To achieve this goal, the individual team members work on subprojects, each of which contributes to the overall software architecture of the vehicle. The focus is on the one hand on interactive trajectory planning with several vehicles in the driving dynamic limit range, and on the other hand on environment perception and localization at high speeds. To achieve these goals, on the one hand the behavior of the opposing racing vehicle must be predicted quickly and reliably, and on the other hand the driving dynamic limit for the control of the vehicle must be determined. The test drives with the racing vehicle, a Dallara IL-15, are then used to evaluate the real-time capability, performance and reliability of the newly developed algorithms.
The Team
The Technical University of Munich (TUM) has decided to participate in the AC@IAC with its own team based on the knowledge of various institutes. The team will develop various functions for the operation of the autonomous racing car and subsequently evaluate them. The team consists of the following members:
| Phillip Karle Teammanager | Project: Motion Predction for Autonomous Driving Prediction Object Detection |
| Regelung | Project: Self-learning Control for Autonomous Cars Control Vehicle Performance |
| Perception | Project: End-to-End Learning for Autonomous Cars Object Detection Object Tracking |
| Perception | Project: Sensorfusion for Perception Mapping Object Detection |
| Prediction | Project: Ethics for Autonomous Driving Prediction Behavioral Planning |
| Path Planning | Project: Trajectory Planning with Game Theory Path Planning Behavioral Planning |
| Tim Stahl Safety | Project: Safety Assessment for Autonomous Cars Path Planning Safety Assessment |
| Path Planning | Project: Trajectory Planning for Autonomous Cars Trajectory Planning Control |
| Control | Project: Energy Management for Racecars Control Vehicle Performance: Energy Management |
| Vehicle Performance | Project: Road Friction Prediction Simulation Vehicle Performance: Road Friction |
Sponsoring
The TUM Autonomous Motorsport Team is supported in this research project by numerous companies and sponsors, which are listed below:
The Software
Within the individual research projects, numerous software has been developed, which is available as open source on the TUM FTM Github Repository:
- Graph-based local trajectory planner for race vehicles in a dynamic environemnt
- Scenario Architect for the creation of short scene snapshots for autonomous driving benchmarks
- Optimization algorithm for the creation of global, optimal raceline
- Path and velocity controller for an autonomous racecar
- Neural Network for Object Detection with Camera and Radar Data
- Vehicle dynamics simulation for autonomous vehicles
- Library with functions for trajectory planning
- Database with maps of international racetracks
- Quasi-static laptime simulation
- Recursive Uncertainty Model Identification
- ORB-SLAM2 Map Saving Extension
Scientific Publications
Betz, J.; Wischnewski, A.; Heilmeier, A.; Nobis, F.; Stahl, T.; Hermansdorfer, L.; Lohmann, B.; Lienkamp, M.; „What can we learn form autonomous level 5 Motorsport?“ at the 10th international Chassis Symposium “Chassis.Tech Plus 2019”, Munich, Juni 2018, doi: 10.1007/978-3-658-22050-1_12
Heilmeier, A.; Graf, M.; Lienkamp, M.;"A Race Simulation for Strategy Decisions in Circuit Motorsports" at the 21th International Conference on Intelligent Transportation Systems (ITSC) 2018, Hawaii, October 2018,doi: 10.1109/ITSC.2018.8570012
Heilmeier, A.; Wischnewski, A.; Hermansdorfer, L.; Betz, J.; Lienkamp, M.; Lohmann, B.:"Minimum curvature trajectory planning and control for an autonomous race car" in Vehicle System Dynamics - International Journal of Vehicle Mechanics and Mobility, pp. 1–31, June 2019, doi: 10.1080/00423114.2019.1631455
Stahl, T.; Wischnewski, A.; Betz, J.; Lienkamp, M: “ROS-based localization of a race vehicle at high-speed using LIDAR“ in E3S Web of Conferences, vol. 95, p. 4002, 2019, doi: 10.1051/e3sconf/20199504002
Betz, J.; Wischnewski, A.; Heilmeier, A.; Nobis, F.; Stahl, T.; Hermansdorfer, L.; Lienkamp, M.; „A Software Architecture for an Autonomous Racecar“ at the 89th Vehicular Technology Conference (VTC2019-Spring), Kuala Lumpur, 2019, doi: 10.1109/VTCSpring.2019.8746367
Nobis, F.; Betz, J. ; Hermansdorfer, L.; Lienkamp, M.: “Autonomous Racing: A Comparison of SLAM Algorithms for Large Scale Outdoor Environments“ in Proceedings of the 2019 3rd International Conference on Virtual and Augmented Reality Simulations - ICVARS ’19, 2019, doi: 10.1145/3332305.3332319
Palafox, P.; Betz, J.; Nobis, F.; Riedl, K.; Lienkamp, M.: "Fusing Semantic Segmentation and Monocular Depth Estimation for Enabling Autonomous Driving in Roads Without Lane Lines" in Sensors, vol. 19, no. 14, p. 3224, Jul. 2019, doi: 10.3390/s19143224
Heilmeier, A.; Geisslinger, M.; Betz, J.;"A Quasi-Steady-State Lap Time Simulation for Electrified Race Cars" at the 14th International Conference on Ecological Vehicles and Renewable Energies (EVER2019), Monaco, 2019, doi: 10.1109/EVER.2019.8813646
Wischnewski, A.; Stahl, T.; Betz, J.; Lohmann, B.; „Vehicle Dynamics State Estimation and Localization for High Performance Race Cars “ IFAC-PapersOnLine, vol. 52, no. 8, pp. 154–161, 2019, doi: 10.1016/j.ifacol.2019.08.064
Stahl, T.; Wischnewski, A.; Betz, J.; Lienkamp, M: “Multilayer Graph-Based Trajectory Planning for Race Vehicles in Dynamic Scenarios“ in 2019 IEEE Intelligent Transportation Systems Conference (ITSC), 2019, doi: 10.1109/ITSC.2019.8917032
Hermansdorfer, L.; Betz, J.; Lienkamp, M: “ A Concept for Estimation and Prediction of the Tire-Road Friction Potential for an Autonomous Racecar“ in 2019 IEEE Intelligent Transportation Systems Conference (ITSC), 2019, doi: 10.1109/ITSC.2019.8917024
Herrmann, T.; Christ, F.; Betz, J.; Lienkamp, M: “Energy Management Strategy for an Autonomous Electric Racecar using Optimal Control “ in 2019 IEEE Intelligent Transportation Systems Conference (ITSC), 2019, doi: 10.1109/ITSC.2019.8917154
Wischnewski, A.; Betz, J.; Lohmann, B.: “A Model-Free Algorithm to Safely Approach the Handling Limit of an Autonomous Racecar“ in 2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE 2019), Graz, Austria , 2019, doi: 10.1109/ICCVE45908.2019.8965218
Betz, J.; Wischnewski, A.; Heilmeier, A., Nobis, F.; Stahl, T.; Hermansdorfer, L.; Herrmann, T.; Lienkamp, M.;: “A Software Architecture for the Dynamic Path Planning of an Autonomous Racecar at the Limits of Handling“ in 2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE 2019), doi: 10.1109/ICCVE45908.2019.8965238
Nobis, F.; Geisslinger, M.; Weber, M.; Betz, J.; Lienkamp, M.: "Learning-based Radar and Camera Sensor Fusion Architecture for Object Detection," in 2019 Sensor Data Fusion: Trends, Solutions, Applications (SDF), doi: 10.1109/SDF.2019.8916629
Christ, F.; Wischnewski, A.; Heilmeier, A.; Lohmann, B.: "Time-Optimal Trajectory Planning for a Race Car Considering Variable Tire-Road Friction Coefficients" in Vehicle System Dynamics - International Journal of Vehicle Mechanics and Mobility, doi: 10.1080/00423114.2019.1704804
Betz, J.; Heilmeier, A.; Wischnewski, A.; Stahl, T.; Lienkamp, M.;: “Autonomous Driving - A Crash Explained in Detail“ in Applied Sciences, vol. 9, no. 23, p. 5126, Nov. 2019, https://doi.org/10.3390/app9235126
Stahl, T.; Betz. J; Diermeyer, F. : “Runtime Verification Concept for Autonomous Vehicles – Exemplary Study for the Planning Module of an Autonomous Race Vehicle“ in 23rd IEEE International Conference on Intelligent Transportation Systems (ITSC), September 2020, Rhodes, Greece, accepted, Fulltext (Preprint)
Nobis, F.; Betz. J; Lienkamp, M.: “Exploring the Capabilities and Limits of 3D Monocular Object Detection - A Study on Simulation and Real World Data“ in 23rd IEEE International Conference on Intelligent Transportation Systems (ITSC), September 2020, Rhodes, Greece, accepted, Fulltext (Preprint)
Herrmann, T.; Passigato, F.; Betz. J; Lienkamp, M.: “Minimum Race-Time Control-Strategy for an Autonomous Electric Racecar“ in 23rd IEEE International Conference on Intelligent Transportation Systems (ITSC), September 2020, Rhodes, Greece, accepted, Fulltext (Preprint)
Stahl, T.; Betz. J: “A Scenario Generator for Evaluating Path Planning Algorithms for Autonomous Driving” in 15th International Conference on Ecological Vehicles and Renewable Energies (EVER2020), May 2020, Monaco, France, accepted, Fulltext (Preprint)
Nobis, F.; Papanikolaoi, O.; Betz, J.; Lienkamp, M: “Persistent Map Saving for Visual Localization for Autonomous Vehicles: An ORB-SLAM Extension” in 15th International Conference on Ecological Vehicles and Renewable Energies (EVER2020), May 2020, Monaco, France, accepted, Fulltext(Preprint)
Hermansdorfer, L.; Betz, J.; Lienkamp, M: “Benchmarking of a software stack for autonomous racing against a professional human race driver” in 15th International Conference on Ecological Vehicles and Renewable Energies (EVER2020), May 2020, Monaco, France, accepted, Fulltext(Preprint)
Heilmeier, A.; Graf, M.; Betz, J.; Lienkamp, M.: ““Application of Monte Carlo Methods to Consider Probabilistic Effects in a Race Simulation for Circuit Motorsport,” Applied Sciences, vol. 10, no. 12, p. 4229, Jun. 2020, doi: https://doi.org/10.3390/app10124229
Heilmeier, A.; Thomaser, A.; Graf, M.; Betz, J.: “Virtual Strategy Engineer: Using Artificial Neural Networks for Making Race Strategy Decisions in Circuit Motorsport,” Applied Sciences, vol. 10, no. 21, p. 7805, Nov. 2020, doi: https://doi.org/10.3390/app10217805
Wischnewski, A.; Betz, J.; Lohmann, B.: „Real-Time Learning of Non-Gaussian Uncertainty Models for Autonomous Racing“ in 59th IEEE Conference on Decision and Control (CDC), Jeju Island, Republic of Korea, December 2020, accepted
Herrmann, T.; Wischnewski, A.; Hermansdorfer, L.; Betz, J.; Lienkamp, M.: „Real-Time Adaptive Velocity Optimization for Autonomous Electric Race Cars“ in IEEE Transactions on Intelligent Vehicles, under Review
Hermandorfer, L.; Trauth, R.; Betz, J.; Lienkamp, M.: „End-to-End Neural Network vor Vehicle Dynamics Modeling“ in 3rd IEEE Conference on Optimization and Modeling of Complex Systems, Agadir, Morocco, December 2020, under review