Adam Molin
Adam Molin has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Brian Hsuan-Cheng Liao
DENSO AUTOMOTIVE, Eching, Bavaria, Germany
1 shared publication - Damir Safin
Fortiss GmbH, Research Institute of the Free State of Bavaria, Germany
1 shared publication Hasan Esen
Automotive Deutschland GmbH,Corporate R&D department of DENSO,Eching,Germany,85386
1 shared publication- Lev Sorokin
Technical University of Munich, Munich, Germany and BMW Group, Munich, Germany
1 shared publication - Maximilian Kneissl
Volvo Autonomous Solutions, Gothenburg, Sweden
1 shared publication Sandra Hirche
Technische Universität München,Institute for Information- oriented Control,München,Germany,80290
1 shared publication
Latest Publications
- Open Access
- 14 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 94-98
OpenSBT: A Modular Framework for Search-based Testing of Automated Driving Systems
Search-based software testing (SBST) is an effective and efficient approach for testing automated driving systems (ADS). However, testing pipelines for ADS testing are particularly challenging as they involve integrating complex driving simulation platforms and establishing communication protocols and APIs with the desired search algorithm. This complexity prevents a wide adoption of SBST and thorough empirical comparative experiments with different simulators and search approaches. We present OpenSBT, an open-source, modular and extensible framework to facilitate the SBT of ADS. With OpenSBT, it is possible to integrate simulators with an embedded system under test, search algorithms and fitness functions for testing. We describe the architecture and show the usage of our framework by applying different search algorithms for testing Automated Emergency Braking Systems in CARLA as well as in the industrial and high-fidelity simulator Prescan in collaboration with our industrial partner DENSO. OpenSBT is available at https://git.fortiss.org/opensbt. A demo video is provided here: https://www.youtube.com/watch?v=qi_CTTzrk5s.
- 14 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 94-98
Open AccessOpenSBT: A Modular Framework for Search-based Testing of Automated Driving Systems
Search-based software testing (SBST) is an effective and efficient approach for testing automated driving systems (ADS). However, testing pipelines for ADS testing are particularly challenging as they involve integrating complex driving simulation platforms and establishing communication protocols and APIs with the desired search algorithm. This complexity prevents a wide adoption of SBST and thorough empirical comparative experiments with different simulators and search approaches. We present OpenSBT, an open-source, modular and extensible framework to facilitate the SBT of ADS. With OpenSBT, it is possible to integrate simulators with an embedded system under test, search algorithms and fitness functions for testing. We describe the architecture and show the usage of our framework by applying different search algorithms for testing Automated Emergency Braking Systems in CARLA as well as in the industrial and high-fidelity simulator Prescan in collaboration with our industrial partner DENSO. OpenSBT is available at https://git.fortiss.org/opensbt. A demo video is provided here: https://www.youtube.com/watch?v=qi_CTTzrk5s.
- Open Access
- 1 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 6687-6693
A One-Step Feasible Negotiation Algorithm for Distributed Trajectory Generation of Autonomous Vehicles
We propose a distributed trajectory generation method for connected autonomous vehicles. It is integrated in an intersection crossing scenario where we assume a given vehicle order provided by a high-level scheduling unit. The multi-vehicle framework is modeled by local independent vehicle dynamics with coupling constraints between neighboring vehicles. Each vehicle in the framework computes in parallel a local model predictive control (MPC) decision, which is shared with its neighbors after conducting a convex Jacobi update step. The procedure can be iteratively repeated within a sampling time-step to improve the overall coordination decisions of the multi-vehicle setup. However, iterations can be stopped after each inter-sampling step with a guaranteed feasible solution which satisfies local and coupling constraints. We construct feasible initial trajectory candidates and propose a method to emulate the centralized solution. This makes the Jacobi algorithm suitable for distributed trajectory generation of autonomous vehicles in low and medium speed driving. Simulation results compare the performance of the distributed Jacobi MPC scheme with the centralized solution and illustrate the feasibility guarantee in an intersection scenario with unforeseen events.
- 1 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 6687-6693
Open AccessA One-Step Feasible Negotiation Algorithm for Distributed Trajectory Generation of Autonomous Vehicles
We propose a distributed trajectory generation method for connected autonomous vehicles. It is integrated in an intersection crossing scenario where we assume a given vehicle order provided by a high-level scheduling unit. The multi-vehicle framework is modeled by local independent vehicle dynamics with coupling constraints between neighboring vehicles. Each vehicle in the framework computes in parallel a local model predictive control (MPC) decision, which is shared with its neighbors after conducting a convex Jacobi update step. The procedure can be iteratively repeated within a sampling time-step to improve the overall coordination decisions of the multi-vehicle setup. However, iterations can be stopped after each inter-sampling step with a guaranteed feasible solution which satisfies local and coupling constraints. We construct feasible initial trajectory candidates and propose a method to emulate the centralized solution. This makes the Jacobi algorithm suitable for distributed trajectory generation of autonomous vehicles in low and medium speed driving. Simulation results compare the performance of the distributed Jacobi MPC scheme with the centralized solution and illustrate the feasibility guarantee in an intersection scenario with unforeseen events.