Survey of the latest transportation research offered by 12 MIT faculty each presenting their ongoing research. Students are required to attend the classes, read the assigned articles, and write a brief reflection memo.

Explores deep learning (DL) methods for urban mobility applications. Covers concepts of algorithmic prediction, interpretability, causality, and fairness in the context of urban mobility system design and policy making. Topics include demand prediction at both individual and aggregate levels, decision making with and without uncertainty, vehicle and ride sharing, built environment and travel behavior, traffic prediction and control, maps and information provision, and multimodal system design. Students learn intuitions and methods in DNN, CNN, RNN and reinforcement learning, build hands-on models using real-world datasets, and design and implement group projects. At the intersection of machine learning methods and urban mobility applications, the course seeks to reconcile the tension between generic-purpose models and domain-specific knowledge. Furthermore, the course envisions and critically reflects on how machine learning methods shape transportation research and mobility industry, and examines the potentials and pitfalls of their applications in urban mobility business and policies.

Covers the mathematical foundations and state-of-the-art implementations of algorithms for vision-based navigation of autonomous vehicles (e.g., mobile robots, self-driving cars, drones). Topics include geometric control, 3D vision, visual-inertial navigation, place recognition, and simultaneous localization and mapping. Provides students with a rigorous but pragmatic overview of differential geometry and optimization on manifolds and knowledge of the fundamentals of 2-view and multi-view geometric vision for real-time motion estimation, calibration, localization, and mapping. The theoretical foundations are complemented with hands-on labs based on state-of-the-art mini race car and drone platforms. Culminates in a critical review of recent advances in the field and a team project aimed at advancing the state-of-the-art.

Intensive one-week subject that uses the Boeing 767 aircraft as an example of a system of systems. Focuses on design drivers and compromises, system interactions, and human-machine interface. Morning lectures, followed by afternoon desktop simulator sessions. Critique and comparison with other transport aircraft designs. Includes one evening at Boston Logan International Airport aboard an aircraft.

Students design an autonomous vehicle system to satisfy stated performance goals. Emphasizes both hardware and software components of the design and implementation. Entails application of fundamental principles and design engineering in both individual and group efforts. Practice in written and oral communication provided. Students showcase the final design to the public at the end of the term.

Theory and application of probabilistic techniques for autonomous mobile robotics. Topics include probabilistic state estimation and decision making for mobile robots; stochastic representations of the environment; dynamic models and sensor models for mobile robots; algorithms for mapping and localization; planning and control in the presence of uncertainty; cooperative operation of multiple mobile robots; mobile sensor networks; application to autonomous marine (underwater and floating), ground, and air vehicles.

Presents concepts, principles, and algorithmic foundations for robots and autonomous vehicles operating in the physical world. Topics include sensing, kinematics and dynamics, state estimation, computer vision, perception, learning, control, motion planning, and embedded system development. Students design and implement advanced algorithms on complex robotic platforms capable of agile autonomous navigation and real-time interaction with the physical word. Students engage in extensive written and oral communication exercises.

This subject counts as a Control concentration subject. Reinforcement learning (RL) as a methodology for approximately solving sequential decision-making under uncertainty, with foundations in optimal control and machine learning. Finite horizon and infinite horizon dynamic programming, focusing on discounted Markov decision processes. Value and policy iteration. Monte Carlo, temporal differences, Q-learning, and stochastic approximation. Approximate dynamic programming, including value-based methods and policy space methods. Special topics at the boundary of theory and practice in RL. Applications and examples drawn from diverse domains. While an analysis prerequisite is not required, mathematical maturity is necessary. Enrollment limited

Provides an introduction to tools used for probabilistic reasoning in the context of discrete systems and processes. Tools such as the probabilistic method, first and second moment method, martingales, concentration and correlation inequalities, theory of random graphs, weak convergence, random walks and Brownian motion, branching processes, Markov chains, Markov random fields, correlation decay method, isoperimetry, coupling, influences and other basic tools of modern research in probability will be presented. Algorithmic aspects and connections to statistics and machine learning will be emphasized.

Topics on the engineering and analysis of network protocols and architecture, including architectural principles for designing heterogeneous networks; transport protocols; Internet routing; router design; congestion control and network resource management; wireless networks; network security; naming; overlay and peer-to-peer networks. Readings from original research papers.

Introduces principles, algorithms, and applications of machine learning from the point of view of modeling and prediction; formulation of learning problems; representation, over-fitting, generalization; classification, regression, reinforcement learning; and methods such as linear classifiers, feed-forward, convolutional, and recurrent networks. Students taking graduate version complete different assignments. Meets with 6.036 when offered concurrently. Recommended prerequisites: 18.06 and 6.006. Enrollment limited; no listeners.

Principles, techniques, and algorithms in machine learning from the point of view of statistical inference; representation, generalization, and model selection; and methods such as linear/additive models, active learning, boosting, support vector machines, non-parametric Bayesian methods, hidden Markov models, Bayesian networks, and convolutional and recurrent neural networks. Recommended prerequisite: 6.036 or other previous experience in machine learning.

Hands-on analysis of data demonstrates the interplay between statistics and computation. Includes four modules, each centered on a specific data set, and introduced by a domain expert. Provides instruction in specific, relevant analysis methods and corresponding algorithmic aspects. Potential modules may include medical data, gene regulation, social networks, finance data (time series), traffic, transportation, weather forecasting, policy, or industrial web applications. Projects address a large-scale data analysis question. Students taking graduate version complete additional assignments. Limited enrollment; priority to Statistics and Data Science minors and to juniors and seniors.

Introduction to data mining, data science, and machine learning, methods that assist in recognizing patterns, developing models and predictive analytics, and making intelligent use of massive amounts of data collected via the internet, e-commerce, electronic banking, pointof-sale devices, bar-code readers, medical databases, and other sources. Topics include logistic regression, association rules, treestructured classification and regression, cluster analysis, discriminant analysis, and neural network methods. Presents examples of successful applications in credit ratings, fraud detection, marketing, customer relationship management, investments, and synthetic clinical trials. Introduces data-mining software focusing on R. Term project required. Meets with 15.062 when offered concurrently. Expectations and evaluation criteria differ for students taking graduate version; consult syllabus or instructor for specific details.

Introduces data science and machine learning topics in both theory and application. Data science topics include database and API connections, data preparation and manipulation, and data structures. Machine learning topics include model fitting, tuning and prediction, end-to-end problem solving, feature engineering and feature selection, overfitting, generalization, classification, regression, neural networks, dimensionality reduction and clustering. Covers software packages for statistical analysis, data visualization and machine learning. Introduces best practices related to source control, system architecture, cloud computing frameworks and modules, security, emerging financial technologies and software process. Applies teaching examples to logistics, transportation, and supply chain problems.