Chair of software engineering: Dependability

M.Sc. Anil Ranjitbhai Patel

Role

Researcher at the research group Software Engineering: Dependability

Address

M.Sc. Anil Ranjitbhai Patel
TU Kaiserslautern
Building 32, Room 435
P.O. Box 3049
67653 Kaiserslautern
Germany

Tel: +49 (631) 205-3334

Fax: +49 (631) 205-3331

E-mail: patel@cs.uni-kl.de

Research Focus

Dynamic Risk/Safety Management for Autonomous Vehicles

(Safety is defined as freedom from risk and risk is the possibility of suffering harm or loss.)

Autonomous vehicles (AVs) are complex safety-critical systems that operate in an uncertain and dynamic environment. During runtime, the environmental uncertainties and random component failures might result in hazardous events, sometimes even to an accident, if left undetected. Moreover, in the event of random errors, highly integrated automotive systems might suffer from the butterfly effect, which could produce an unannounced unsafe behavior of the system. While AV operates in a dynamic environment, traditional safety assurance mechanisms like Fault Tree Analysis (FTA), Failure Mode Effect and Criticality Analysis (FMECA), etc. are primarily beneficial, but not sufficient to ensure safety as they are based on static worst-case assumptions. It is, therefore, necessary to move from static safety management methods to dynamic safety management approaches. Hazard Analysis and Risk Assessment (HARA) of ISO 26262 assure functional safety of systems by considering: Hazardous events, their associated severity, exposure, and controllability ratings to evaluate an Automotive Safety Integrity Level (ASIL). The entire process, however, is based on the very premise that a human driver is forever available to take control and is thus responsible for the safety of the vehicle. On the contrary, autonomous vehicles (AVs) function without any human intervention. Therefore, Dynamic Risk Assessment (DRA) at runtime is the need of the hour to be a step forward to analyze the current risk of the actual situation at runtime, instead of relying on static worst-case assumptions.

Publications

2021
2021
2020

Master Thesis

  • Arnab Ghosh - ASIL inspired Risk Assessment based on Machine-Learning Classification for Autonomous Vehicle
2021
  • Bavithira Gnanasegaram - Dynamic Risk Assessment in Autonomous Vehicle using Long-Short Term Memory
2021
  • Sinduja Narra - Identifying Factors Influencing Unsafe Behaviors based on Random Forest for Dynamic Risk Assessment in Autonomous Vehicles
2021
  • Dhiraj Dandekar - Prediction of Vehicle behavior by Simulation of Faults in Lateral Control of Highly Automated Commercial Vehicles and Derivation of Requirements for a Redundancy Concept
2021
  • Michael Wittemaier - Modelling of an Adaptable Autonomous System using Adaptation Techniques and Machine Learning
2021
  • Kaivlya Patel - Parameterized Tool for Tradespace Analysis for Fact-based Concept Decisions in Systems Engineering
2021
  • Clement John Shaji - Diversity for Safety and Security of Autonomous Vehicles against Accidental and Deliberate Faults
2021
  • Ali Faraz - Dynamic Risk Assessment for Adaptable Autonomous Systems using Machine-Learning technique
2020
Zum Seitenanfang