| Project Id
|
BRJP26100077
|
| Project Detail
|
| Project Title
|
Effective Management of Traffic Dynamics in Connected and Autonomous Vehicle Environments
|
| Senior Supervision Team (BITS)
|
| Supervisor name and Title
|
Prof. Maripini Himabindu
|
School or Department (or company, if applicable)
|
BITS PILANI, PILANI CAMPUS
|
|
|
|
Email ID
|
maripini.himabindu@pilani.bits-pilani.ac.in
|
| URL for more info
|
https://www.bits-pilani.ac.in/pilani/maripini-himabindu/
|
| a) Are you currently supervising a BITS or RMIT HDR student?
|
NO
|
| Please comment how many you are supervising
|
|
| b) Have you supervised an offshore candidate before?
|
NO
|
| If no, what support structures do you have in place?
|
|
| If yes, please elaborate
|
|
| Senior Supervision Team (RMIT)
|
| Supervisor name and Title
|
Reza Hoseinnezhad
|
School or Department (or company, if applicable)
|
STEM
|
|
|
|
Email ID
|
rezah@rmit.edu.au
|
| URL for more info
|
https://www.rmit.edu.au/profiles/h/reza-hoseinnezhad
|
| a) Are you currently supervising a BITS or RMIT HDR student?
|
YES
|
| Please comment how many you are supervising
|
10
|
| b) Have you supervised an offshore candidate before?
|
YES
|
| If no, what support structures do you have in place?
|
|
| If yes, please elaborate
|
I am currently supervising a student jointly with ACSIR, and we meet online every week and discuss her progress. Her project is both fundamental and practical, and the fundamental aspects are mainly covered by me, and for the experimental parts she uses her ACSIR facilities. A similar plan is to be in place for this project we are proposing.
|
| Other Supervisors (BITS)
|
| Supervisor name and Title
|
Vinayak Malaghan
|
School or Department (or company, if applicable)
|
BITS PILANI, PILANI CAMPUS
|
| Phone Number (Optional)
|
+91-7975188275
|
Email ID
|
vinayak.malaghan@pilani.bits-pilani.ac.in
|
| URL for more info
|
https://www.bits-pilani.ac.in/pilani/vinayak-devendra-malaghan/
|
| Other Supervisors (BITS)
|
| Supervisor name and Title
|
Amirali Khodadadian Gostar
|
School or Department (or company, if applicable)
|
STEM
|
| Phone Number (Optional)
|
+61399254593
|
Email ID
|
amirali.khodadadian@rmit.edu.au
|
| URL for more info
|
https://www.rmit.edu.au/profiles/k/amirali-khodadadian
|
| Field of Research (For Codes)
|
| 350902 | Intelligent mobility | 30.00 |
| 400203 | Automotive mechatronics and autonomous systems | 50.00 |
| 460207 | Modelling and simulation | 20.00 |
|
| Project Description
|
|
This PhD project develops a situational-awareness-driven approach to managing traffic dynamics in Connected and Autonomous Vehicle (CAV) environments operating under mixed traffic conditions. The key premise is that near-term road networks will include CAVs alongside human-driven vehicles, pedestrians, and cyclists, creating uncertainty and partial observability that conventional infrastructure-centric traffic management cannot resolve with sufficient resolution or timeliness. Building on Reza Hoseinnezhad’s prior work on Random Finite Set (RFS) multi-target tracking—particularly Labeled Multi-Bernoulli (LMB) filtering—the project defines situational awareness as the real-time probabilistic knowledge of surrounding moving agents: their number, identities, classes (car, truck, motorbike, bicycle, pedestrian), and states (position, velocity, heading/turn rate, and manoeuvre intent where feasible).
The methodology begins with each CAV producing local multi-object posteriors from onboard sensing and then forming enhanced traffic awareness through centralised or distributed fusion across the connected fleet under bandwidth and latency constraints. The fused multi-agent states are mapped to traffic-level representations over a road-network graph, enabling estimation of dynamic variables such as density, flow, queue formation, congestion propagation, and risk fields around vulnerable road users. On top of these estimates, the project develops traffic management and control strategies that exploit the situational intelligence in both centralised modes (e.g., adaptive signal control and corridor coordination) and distributed modes (e.g., cooperative speed harmonisation, gap creation, platoon negotiation, and decentralised intersection negotiation). The research explicitly evaluates performance under varying CAV penetration rates and realistic human-driver uncertainty.
|
| Project Deliverable/Outcomes
|
|
The project will deliver a set of scientific, algorithmic, and system-level outcomes that establish a direct pathway from LMB-based situational awareness to practical traffic management in mixed-autonomy environments.
A primary outcome will be new methods that transform multi-object posteriors produced by Labeled Multi-Bernoulli (LMB) filtering into traffic-scale state representations. This includes principled mappings from agent-level estimates (number of objects, labelled tracks, class, kinematics, and motion intent where available) to mesoscopic and macroscopic variables such as link density, flow, queue length, congestion growth/shockwave indicators, and safety-risk fields, with explicit uncertainty characterisation.
A second major outcome will be scalable cooperative fusion architectures for traffic operations, covering both centralised and distributed settings. These will address label consistency across vehicles, redundancy and double counting, asynchronous updates, and realistic V2X constraints (latency, bandwidth, packet loss). The result will be a robust “traffic situational awareness layer” that can support intersection-, corridor-, and network-level decision making under partial CAV penetration.
A third outcome will be traffic control and optimisation strategies that exploit this situational intelligence. In centralised modes, the project will deliver perception-informed adaptive signal control and corridor/network coordination policies. In distributed modes, it will deliver cooperative CAV strategies including speed harmonisation, gap creation, platoon negotiation, and decentralised intersection negotiation designed to remain effective in the presence of human-driven vehicles and vulnerable road users.
System outputs will include an integrated simulation and evaluation framework coupling LMB tracking, cooperative fusion, traffic state inference, and closed-loop control. Performance will be benchmarked against conventional infrastructure-only and heuristic approaches using throughput, travel-time variability, stop–start reduction, and safety surrogate metrics (e.g., conflict likelihood/time-to-collision risk fields), including robustness testing under degraded communications.
Scholarly and translational outcomes include high-quality publications, reusable software modules for cooperative traffic intelligence, and potential IP in fusion/control architectures for mixed-traffic CAV management.
|
| Research Impact Themes
|
| AI/ML and Data Analytics / Data Science with a focus on applications/translation in | Transportation & Logistics |
|
| Which RMIT Sustainable Development Goal (SDG) does your project align to
|
|
SUSTAINABLE CITIES AND COMMUNITIES
|
| Which RMIT Enabling Impact Platform (EIP) does your project align to
|
|
URBAN FUTURES
|
| Which RMIT Program code will this project sit under?
|
|
DR216P23 PhD (Mech,Manu & Mech Eng)
|
| Student Capabilities and Qualifications
|
|
1 - Multi-target tracking and probabilistic estimation fundamentals, 2 - Strong scientific programming and algorithm implementation skills
|
|
3 - Traffic modelling, ITS, or networked dynamical systems background 4 - Distributed estimation/control and V2X awareness
|
|
Expected qualifications Minimum (expected) MSc or MTech in a closely related discipline such as Electrical/Electronic Engineering, Mechatronics, Robotics/Autonomous Systems, Computer Science, AI, Signal Processing, or Intelligent Transport Systems.
|
| Preferred discipline of Student
|
| Computing: Computer Science, Computer System Security, Software Engineering, Cyber Security & Cyber Physical Systems |
| Electrical and Electronics Engineering, Power Engineering |
| Mechanical Enineering, Mechanics, Mechatronics, Aerospace Eng, Hypersonics |
| Robotics, Sensors, Signal Processing, Control Engineering |
|