Course Structure for MTech in Smart Mobility and Logistics Systems

Numbers in brackets indicate instruction credits and lab credits.

Foundational Courses (10 credits)

• Applied Mathematics (3:0)
• Introduction to Algorithms and Software Programming (2:1)
• Capstone in Mobility Systems (1:2)
• Seminar (1:0)

Softcore Pool A (Min 15 credits)

• Introduction to Multi-Modal Mobility Systems (3:1)
• Logistics & Freight Modelling (3:1)
• Transportation Demand and Supply Modelling (3:1)
• Network Science & Optimization (3:1)
• Machine Learning for Cyber Physical and Mobility Systems (3:1)
• Operations Research for Mobility Management (3:0)
• Choice Modelling (3:0)
• Pavement Engineering (3:0)
• Transportation Safety & Injury Prevention Principles (3:1)

Softcore Pool B (Min. 6 credits)

• Human Machine Interaction (3:0)
• Behavioural Science (2:1)
• Public Policy Theory and Process (2:0)
• Principles and Applications of GIS and Remote Sensing (3:1)
• Theory & Applications of Bayesian Learning (3:0)
• Edge AI (3:0)
• Introduction to Data Science (3:1)
• Introduction to Scalable Systems (3:1)
• Scalable Systems for Data Science (3:1)
• ML for Data Science (3:0)
• Deep Learning for Computer Vision (3:1)
• Modelling and Simulation (3:1)
• Computational Methods of Optimization (3:1)
• Linear and Nonlinear Optimization (3:0)
• Computer Vision (3:0)
• Design for Internet of Things (3:0)

Electives (6 credits)

Project (27 credits)

Softcore Pool A Course Description

Introduction to Multi-modal Mobility Systems

Designing a transportation system; modes of transportation; characteristics of user, vehicle, and road; traffic engineering studies; geometric design principles; traffic analysis; transportation planning; transportation safety; fundamentals of traffic flow; traffic control basics; capacity and level of service; multi-scale modelling; sustainable transportation systems; public transit; multi-modal transportation; intelligent transportation systems; and smart cities.

Logistics & Freight Modelling

Introduction to freight and logistics systems, Introduction to mathematical modelling, TSP and VRP, Matching and scheduling problems, Location problems, Heuristics, Collaborative logistics, Inventory modelling, Supply chains, Planning under Uncertainty, Revenue management, Freight movement analysis, Demand estimation and forecasting.

Transportation Demand and Supply Modelling

Travel demand-supply interactions and equilibrium; Aggregate modelling methods for travel demand analysis (generation, spatial and temporal distribution, and modal split of travel); Statistical and econometric methods for transportation data analysis; Discrete choice models for travel behaviour analysis; Agent-based methods for travel demand analysis; Traffic assignment in transportation networks; Basics of Convex optimization; Shortest path algorithms; Wardrop user equilibrium; System optimum; Link-based algorithms (Method of successive averages, Frank-Wolfe) and their implementation.

Network Science & Optimization

Introduction to Networks; Shortest paths (Label setting and label correcting methods, A* algorithm, Contraction hierarchies); Max flows and Min cost problems (Augmenting path method, Cycle cancelling and successive shortest path methods); Spanning Trees; Traveling salesman and Vehicle routing problems; Random networks, Centrality measures (Small worlds, Power laws, Scale-free properties); Evolution of networks; Spreading phenomenon; Introduction to GNNs (Graph Neural Networks).

Transportation Safety & Injury Prevention Principles

Introduction to transportation basics; traffic safety as a public health hazard; DALYs (Disability-Adjusted Life Years); international crash data trends; India crash data trends; safe systems approach and Vision Zero; crash data analysis; proactive and reactive safety interventions; IRC codes and safety audits; vulnerable road users; crash modification factors and safety performance functions; methods of costing crashes; surrogate safety measures.

Machine Learning for Cyber-Physical and Mobility Systems

Introduction to CPS (Cyber-Physical Systems) and Mobility problems; Data types and quality issues in CPS, data pre-processing; Model Selection: Model evaluation, model complexity, Bias-variance tradeoff; Regression analysis – Linear and Non-Linear Regression, Poisson Regression; Classification Techniques: Logistic Regression, Decision tree, Naïve Bayes, k-NN, SVM; Ensemble Models - Bagging, Boosting, Stacking; Basic Optimization techniques for ML; Neural networks - Perceptron, ANN (Artificial Neural Networks), Fundamentals of Deep Learning; Clustering: k-means clustering, hierarchical clustering, Gaussian mixture model with EM, Spectral Clustering; Cluster Validation (AIC, AICc); Dimensional reduction: Linear dimension reduction (e.g., PCA), Non-linear dimension reduction (Kernel PCA, MDS, ISOMAP, t-SNE, UMAP); Anomaly Detection (AD): Types of Anomalies, Anomaly Evaluation, Supervised and Unsupervised AD; Semi-supervised Learning and Active Learning; Weekly hands-on programming tutorials and case studies on CPS and mobility datasets/applications.

Operations Research for Mobility Management

This course will introduce operations research (OR) techniques applied to cyber-physical systems (CPS), with an emphasis on decision making for mobility management. Urban mobility is evolving from a fixed supply chain that delivers process-driven travel to a dynamic ecosystem that delivers on-demand services. This new mobility model requires optimization across multiple systems such as transportation, parking, electric vehicle charging and vehicle-to-grid services, etc. The complexity, therefore, arises from the large scale of operations; heterogeneity of system components; dynamic and uncertain operating conditions; and goal-driven decision making and control with time-bounded task completion guarantees.

The focus in this course will be on various classical optimization techniques and learning to optimize approaches that can be applied to solve operational problems at scale in the urban mobility domain. Examples of some decision questions include planning/scheduling charging operations for a fleet of electric vehicles; dynamic pricing for charging demand management; electric vehicle route planning for last-mile delivery of goods and other valued-added services (such as selling energy back to the grid); operations management of mixed fleet of vehicles; etc. Selective operations research topics such as linear programming and combinatorial optimization; dynamic programming; sequential decision making under uncertainty; reinforcement learning; etc.; will be covered to understand the mathematical concepts for problem solving in mobility management.

Choice Modelling

Individual choice theories; Binary choice models; Unordered multinomial choice models (multinomial logit and multinomial probit); Ordered response models (ordered logit, ordered probit, generalized ordered response); Maximum likelihood estimation; Sampling-based estimation (choice-based samples and sampling of alternatives); Multivariate extreme value models (nested logit, cross-nested logit); Mixture models (mixed logit and latent class models); Mixed multinomial probit; Integrated choice and latent variable models; Discrete-continuous choice models with corner solutions; Alternative estimation methods (EM, analytic approximations, simulation); Applications to travel demand analysis.

Pavement Engineering

Introduction to pavement engineering; design of flexible and rigid pavements: selection of pavement design input parameters, traffic loading and volume, material characterization, drainage, failure criteria; pavement design of overlays; pavement performance evaluation; non-destructive tests for pavement; IRC, AASHTO design codes; maintenance and rehabilitation of pavements.