Yuvaraj Selvaraj | Chalmers University of Technology (original) (raw)
Uploads
Papers by Yuvaraj Selvaraj
2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC)
Lane change manoeuvres are complex driving manoeuvres to automate since the vehicle has to antici... more Lane change manoeuvres are complex driving manoeuvres to automate since the vehicle has to anticipate and adapt to intentions of several surrounding vehicles. Selecting a suitable gap to move/merge into the adjacent lane and performing the lane change can be challenging, especially in dense traffic. Existing gap selection methods tend to be either cautious or opportunistic, both of which directly affect the overall availability and safety of the autonomous feature. In this paper we present a method which enables the autonomous vehicles to increase the availability of lane change manoeuvres by reducing the required margins to ensure a safe manoeuvre. The required safety margins are first calculated by making use of the steering and braking capability of the vehicle. It is then shown that this method can be used to perform autonomous lane changes in dense traffic situations with small inter-vehicle gaps. The proposed solution is evaluated by using Model Predictive Control (MPC) to plan and execute the complete motion trajectory.
The field of highly autonomous ground vehicle systems has been the focus of research in both, aca... more The field of highly autonomous ground vehicle systems has been the focus of research in both, academia and industry in the recent decades and is expected to be so in the near future. The work in this thesis focuses on one aspect of highly autonomous vehicles - motion planning in complex traffic environments. The scope of this thesis is limited to motion planning for autonomous lane change and lane change abortion manoeuvres in dense urban traffic scenarios. The purpose of the work is to tackle the problem of autonomous lane change driving in uncertain traffic environments where the vehicle has to anticipate and adapt to behaviour of the surrounding vehicles. The solution is presented as a robust algorithm which is tolerant to uncertainties in the planning horizon. Safety is guaranteed by modelling the safety critical areas around the surrounding vehicles which the autonomous vehicle should not enter in order to plan an evasive action. The problem of motion planning during the entire...
Proceedings of the 23rd ACM/IEEE International Conference on Model Driven Engineering Languages and Systems: Companion Proceedings, 2020
The correctness of autonomous driving software is of utmost importance as incorrect behaviour may... more The correctness of autonomous driving software is of utmost importance as incorrect behaviour may have catastrophic consequences. Though formal model-based engineering techniques can help guarantee correctness, challenges exist in widespread industrial adoption. One among them is the model construction problem. Manual construction of formal models is expensive, error-prone, and intractable for large systems. Automating model construction would be a great enabler for the use of formal methods to guarantee software correctness and thereby for safe deployment of autonomous vehicles. Such automated techniques can be beneficial in software design, re-engineering, and reverse engineering. In this industrial case study, we apply active learning techniques to obtain formal models from an existing autonomous driving software (in development) implemented in MATLAB. We demonstrate the feasibility of active automata learning algorithms for automotive industrial use. Furthermore, we discuss the ...
Development of safety critical systems requires a risk management strategy to identify and analys... more Development of safety critical systems requires a risk management strategy to identify and analyse hazards, and apply necessary actions to eliminate or control them as malfunctions could be catastrophic. Fault Tree Analysis (FTA) is one of the most widely used methods for safety analysis in industrial use. However, the standard FTA is manual, informal, and limited to static analysis of systems. In this paper, we present preliminary results from a model-based approach to address these limitations using Supervisory Control Theory. Taking an example from the Fault Tree Handbook, we present a systematic approach to incrementally obtain formal models from a fault tree and verify them in the tool Supremica. We present a method to calculate minimal cut sets using our approach. These compositional techniques could potentially be very beneficial in the safety analysis of highly complex safety critical systems, where several components interact to solve different tasks.
Correctness of autonomous driving systems is crucial as incorrect behaviour may have catastrophic... more Correctness of autonomous driving systems is crucial as incorrect behaviour may have catastrophic consequences. Many different hardware and software components (e.g. sensing, decision making, actuation, and control) interact to solve the autonomous driving task, leading to a level of complexity that brings new challenges for the formal verification community. Though formal verification has been used to prove correctness of software, there are significant challenges in transferring such techniques to an agile software development process and to ensure widespread industrial adoption. In the light of these challenges, the identification of appropriate formalisms, and consequently the right verification tools, has significant impact on addressing them. In this paper, we evaluate the application of different formal techniques from supervisory control theory, model checking, and deductive verification to verify existing decision and control software (in development) for an autonomous vehi...
2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC)
Lane change manoeuvres are complex driving manoeuvres to automate since the vehicle has to antici... more Lane change manoeuvres are complex driving manoeuvres to automate since the vehicle has to anticipate and adapt to intentions of several surrounding vehicles. Selecting a suitable gap to move/merge into the adjacent lane and performing the lane change can be challenging, especially in dense traffic. Existing gap selection methods tend to be either cautious or opportunistic, both of which directly affect the overall availability and safety of the autonomous feature. In this paper we present a method which enables the autonomous vehicles to increase the availability of lane change manoeuvres by reducing the required margins to ensure a safe manoeuvre. The required safety margins are first calculated by making use of the steering and braking capability of the vehicle. It is then shown that this method can be used to perform autonomous lane changes in dense traffic situations with small inter-vehicle gaps. The proposed solution is evaluated by using Model Predictive Control (MPC) to plan and execute the complete motion trajectory.
The field of highly autonomous ground vehicle systems has been the focus of research in both, aca... more The field of highly autonomous ground vehicle systems has been the focus of research in both, academia and industry in the recent decades and is expected to be so in the near future. The work in this thesis focuses on one aspect of highly autonomous vehicles - motion planning in complex traffic environments. The scope of this thesis is limited to motion planning for autonomous lane change and lane change abortion manoeuvres in dense urban traffic scenarios. The purpose of the work is to tackle the problem of autonomous lane change driving in uncertain traffic environments where the vehicle has to anticipate and adapt to behaviour of the surrounding vehicles. The solution is presented as a robust algorithm which is tolerant to uncertainties in the planning horizon. Safety is guaranteed by modelling the safety critical areas around the surrounding vehicles which the autonomous vehicle should not enter in order to plan an evasive action. The problem of motion planning during the entire...
Proceedings of the 23rd ACM/IEEE International Conference on Model Driven Engineering Languages and Systems: Companion Proceedings, 2020
The correctness of autonomous driving software is of utmost importance as incorrect behaviour may... more The correctness of autonomous driving software is of utmost importance as incorrect behaviour may have catastrophic consequences. Though formal model-based engineering techniques can help guarantee correctness, challenges exist in widespread industrial adoption. One among them is the model construction problem. Manual construction of formal models is expensive, error-prone, and intractable for large systems. Automating model construction would be a great enabler for the use of formal methods to guarantee software correctness and thereby for safe deployment of autonomous vehicles. Such automated techniques can be beneficial in software design, re-engineering, and reverse engineering. In this industrial case study, we apply active learning techniques to obtain formal models from an existing autonomous driving software (in development) implemented in MATLAB. We demonstrate the feasibility of active automata learning algorithms for automotive industrial use. Furthermore, we discuss the ...
Development of safety critical systems requires a risk management strategy to identify and analys... more Development of safety critical systems requires a risk management strategy to identify and analyse hazards, and apply necessary actions to eliminate or control them as malfunctions could be catastrophic. Fault Tree Analysis (FTA) is one of the most widely used methods for safety analysis in industrial use. However, the standard FTA is manual, informal, and limited to static analysis of systems. In this paper, we present preliminary results from a model-based approach to address these limitations using Supervisory Control Theory. Taking an example from the Fault Tree Handbook, we present a systematic approach to incrementally obtain formal models from a fault tree and verify them in the tool Supremica. We present a method to calculate minimal cut sets using our approach. These compositional techniques could potentially be very beneficial in the safety analysis of highly complex safety critical systems, where several components interact to solve different tasks.
Correctness of autonomous driving systems is crucial as incorrect behaviour may have catastrophic... more Correctness of autonomous driving systems is crucial as incorrect behaviour may have catastrophic consequences. Many different hardware and software components (e.g. sensing, decision making, actuation, and control) interact to solve the autonomous driving task, leading to a level of complexity that brings new challenges for the formal verification community. Though formal verification has been used to prove correctness of software, there are significant challenges in transferring such techniques to an agile software development process and to ensure widespread industrial adoption. In the light of these challenges, the identification of appropriate formalisms, and consequently the right verification tools, has significant impact on addressing them. In this paper, we evaluate the application of different formal techniques from supervisory control theory, model checking, and deductive verification to verify existing decision and control software (in development) for an autonomous vehi...