Research
AV Planning and Reasoning
This line of research primarily targets the optimization of planning systems in autonomous vehicles. The focus is on elevating safety measures, streamlining operational efficiency, and aligning system functions with user preferences.
Publications
- Majid Khonji (2023). “Approximability and Efficient Algorithms for Constrained Fixed-Horizon POMDPs with Durative Actions.” The Journal of Artificial Intelligence (AIJ).
- Majid Khonji (2023). “A Fully Polynomial Time Approximation Scheme for Constrained MDPs under Local Transitions.” IEEE Conference on Decision and Control (CDC), Singapore.
- Majid Khonji, Duoaa Khalifa (2023). “Heuristic Search in Dual Space for Constrained Fixed-Horizon POMDPs with Durative Actions.” AAAI Conference on Artificial Intelligence (AAAI), Washington, DC, US.
- Rashid Alyassi, Majid Khonji (2021). “Dual Formulation for Chance Constrained Stochastic Shortest Path with Application to Autonomous Vehicle Behavior Planning.” 60th IEEE conference on Decision and Control (CDC), Austin, Texas, US. [paper, code]
- Sungkweon Hong, Sang Uk Lee, Xin Huang, Majid Khonji, Rashid Alyassi, Brian C. Williams (2021). “An Anytime Algorithm for Chance Constrained Stochastic Shortest Path Problems and Its Application to Aircraft Routing.” IEEE International Conference on Robotics and Automation (ICRA), Xi’an, China. [paper]
- Rashid Alyassi, Majid Khonji, Xin Huang, Sungkweon Hong, Jorge Dias (2021). “Contingency-Aware Intersection System for Autonomous and Human-Driven Vehicles with Bounded Risk.” IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), New York, USA. [paper]
- Majid Khonji, Rashid Al Yassi, Jorge Dias, Fahad Al Maskari, Lakmal Seneviratne (2020). “A Risk-Aware Architecture for Autonomous Vehicle Operation Under Uncertainty.” IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), Abu Dhabi, UAE.
- Majid Khonji, Ashkan Jasour, Brian Williams (2019). “Approximability of Constant-horizon Constrained POMDP.” International Joint Conference on Artificial Intelligence (IJCAI), Macao, China. Acceptance rate 17%. [paper]
AV Perception and Situation Awareness
This line of research is dedicated to refining perception and situational awareness capabilities within the field of autonomous vehicles. Upcoming efforts will place emphasis on formulating robust perception systems able to capture and report model uncertainties. Current projects span from detecting and tracking multiple objects, predicting vehicle wheel slip in off-road conditions, to semantic segmentation of underexposed images.
Publications
- Bilal Hassan, Arjun Sharma, Nadya Abdel Madjid, Majid Khonji, Jorge Dias. “TerrainSense: Vision-Driven Mapless Navigation for Unstructured Off-Road Environments. ICRA 2024.” Yokohama. Japan.
- Mohamed Nagy, Majid Khonji, Jorge Dias and Sajid Javed (2023). “DFR-FastMOT: Detection Failure Resistant Tracker for Fast Multi-Object Tracking Based on Sensor Fusion.” IEEE International Conference on Robotics and Automation (ICRA), London, UK. [paper]
- Hamad AlRemeithi, Fakhreddine Zayer, Jorge Dias, Majid Khonji (2023). “Event Vision for Autonomous Off-Road Navigation.” Artificial Intelligence for Robotics and Autonomous Systems Applications. Studies in Computational Intelligence, vol 1093. Springer, Cham. [paper]
- Mustofa Basri, Areg Karapetyan, Bilal Hassan, Majid Khonji, Jorge Dias (2022). “A Hybrid Deep Learning Approach for Vehicle Wheel Slip Prediction in Off-Road Environments.” IEEE international symposium on Robotic and Sensors Environments (ROSE). Abu Dhabi, UAE. [paper]
- Javed, Sajid, Arif Mahmood, Ihsan Ullah, Thierry Bouwmans, Majid Khonji, Jorge Manuel Miranda Dias, and Naoufel Werghi (2022). “A Novel Algorithm Based on a Common Subspace Fusion for Visual Object Tracking.” IEEE Access. [paper]
- Christopher J Holder, Majid Khonji, Jorge Dias (2020). “Input Optimisation Network for Semantic Segmentation of Underexposed Images.” IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), Abu Dhabi, UAE. [paper]
AV System Integration and Electric Mobility
This line of research focuses on the integration of autonomous vehicle systems into smart cities. It entails the development of strategies for mission planning, and efficient electric vehicle charging. The aim is to enhance the efficiency and sustainability of autonomous technologies within urban environments.
Publications
- Bushra Alshehhi, Areg Karapetyan, Khaled Elbassioni, Sid Chi-Kin Chau, Majid Khonji (2023). “DClEVerNet: Deep Combinatorial Learning for Efficient EV Charging Scheduling in Large-scale Networked Facilities.” ACM International Conference on Future Energy Systems (e-Energy), Florida, US
- Rashid Alyassi, Majid Khonji, Areg Karapetyan, Sid Chau, Khaled Elbassioni, Chien-Ming Tseng (2022). “Autonomous Recharging and Flight Mission Planning for Battery-operated Autonomous Drones.” IEEE Transactions on Automation Science and Engineering (T-ASE). [paper]
- Areg Karapetyan, Khaled Elbassioni, Majid Khonji, Sid Chi-Kin Chau (2022).“Approximations for Generalized Unsplittable Flow on Paths with Application to Power Systems Optimization.” Annals of Operations Research (AOR). [paper]
- Areg Karapetyan, Majid Khonji, Sid Chau, Khaled Elbassioni, Hatem Zeineldin, Tareq El-Fouly, Ahmed Al-Durra (2020). “A Competitive Scheduling Algorithm for Online Demand Response in Islanded Microgrids.” IEEE Transactions on Power Systems (TPS).
Pipeline
- Multi-Agent Chance-Constrained Stochastic Shortest Path with Application to Risk-Aware Intelligent Intersection.
- Towards Optimal Last-mile Logistics with Fully-autonomous Contactless Multi-parcel Delivery Robots.
- Online Load Scheduling in Grid-Tied Microgrids Integrated with Electric Vehicle Charging Station: Model Formulation and a Competitive Algorithm.