Skip to main content
See the NJIT or NYU calendar for semester dates. Each week below lists the readings, lecture topics, and deliverables you should complete.
1

Review prerequisites

Python, linear algebra, probability theory, and basic control concepts. See Prerequisites.
2

Review lecture: Introduction to Robotics

AI and robotics from a systems perspective, with autonomous vehicles as the running example.
3

Watch videos

The Robotic AI Agent, A practical map for navigating robotic AI systems. Development Environment Setup, Setting up the ROS2 Docker-based development environment. Mathematical Prerequisites, Review the math foundations needed for the course.
4

Set up your development environment

Follow the Dev Environment guide to install Docker and configure your container.
5

Import the course repositories

Import both repositories to your GitHub account and clone them locally:eng-ai-agents, the development environments, notebooks and dependency setup.turtlebot-maze, the agentic ground-robot demonstration used throughout robotics. See Starter repos.
6

Watch the session recording

FA26-DS685101 AI for Robotics, 8 September 2026, the recording of the hybrid session.
1

Read TIF Chapters 9 & 10

Introduction to learning and gradient-based learning algorithms from Foundations of Computer Vision.
2

Read BISHOP Chapter 4

Single-variable and multivariate models, regularization, and Bayesian linear regression from Deep Learning: Foundations and Concepts.
3

Review lecture: Supervised Learning

Perception subsystem, reflexive agents, the learning problem. See The Learning Problem.
4

Review lecture: Linear Regression

Regression fundamentals and empirical risk minimization. See Linear Regression.
5

Review lecture: SGD Optimization

Stochastic gradient descent for minimizing the empirical risk. See SGD.
6

Read GERON Chapter 4, SGD sections

Read the Gradient Descent, Batch Gradient Descent, Stochastic Gradient Descent, and Mini-Batch Gradient Descent sections from Chapter 4: Training Linear Models.
7

Run the GERON Chapter 4 notebook

Work through the Training Linear Models notebook.
8

Run the SGD notebook

Execute the Predicting Grid Load notebook in your container.
9

Review lecture: Entropy

Information theory principles and cross-entropy. See Entropy.
10

Review lecture: Marginal Maximum Likelihood

Marginal likelihood and parameter estimation. See Marginal Maximum Likelihood.
11

Review lecture: Conditional Maximum Likelihood

Conditional likelihood for supervised learning. See Conditional Maximum Likelihood.
12

Review lecture: Classification Introduction

Classification fundamentals and decision boundaries. See Classification Introduction.
13

Review lecture: Logistic Regression

Binary classification with logistic regression. See Logistic Regression.
14

Watch videos

The Learning Problem, The Vapnik block diagram. Linear Regression, Extracting non-linear patterns with linear models. Gradient Descent, Optimizing complicated functions with iterative methods. Entropy, Information theory principles. Maximum Likelihood Estimation, The workhorse of statistical modeling. Binary Classification, Binary classification and Logistic Regression. Multiclass Classifier, Extending binary classification to multiple classes. Regularization, Controlling capacity so the model generalizes beyond the training set.
1

Read DL Chapters 9 & 10

Convolutional Neural Network architecture and applications.
2

Review lecture: CNN Introduction

Convolution operations, pooling, and spatial feature hierarchies. See CNN Introduction.
3

Review lecture: CNN Layers

Layer types and architectural patterns. See CNN Layers.
4

Review lecture: CNN Architectures and ResNets

ResNet, VGG, and other architectures. See CNN Example Architectures and Feature Extraction with ResNet.
5

Read GERON Chapter 12, CNN sections

Read the Convolutional Layers, Pooling Layers, and CNN Architectures sections from Chapter 12: Deep Computer Vision with CNNs.
6

Run the GERON Chapter 12 notebook

Work through the Deep Computer Vision with CNNs notebook.
7

Submit Assignment 1

Complete and submit Assignment 1.
8

Watch videos

Feature Extraction, Using a simple network to understand how features are extracted. Backpropagation, How to calculate gradients in a neural network. Convolution and Correlation, A linear operation for extracting spatial features. CNN Architectures, Looking inside a CNN layer and understanding architectural patterns. ResNets, Residual Networks and skip connections. Image Classification, The classification task that convolutional architectures are built for. What CNNs Learn, What the learned filters respond to, layer by layer.
1

Review lecture: Detection Metrics

Evaluation metrics for object detection. See Detection Metrics.
2

Review lecture: Object Detection

Detection pipelines and architectures. See Object Detection Introduction.
3

Review lecture: R-CNN

Region-based convolutional neural networks. See R-CNN.
4

Review lecture: Fast R-CNN

Efficient region-based detection. See Fast R-CNN.
5

Review lecture: Faster R-CNN

Region proposal networks and two-stage detection. See Faster R-CNN.
6

Watch videos

Introduction to Object Detection, Object detection in a physical security application. Computer Vision Datasets, What types of annotations are used in computer vision? Region-based Object Detectors, R-CNN, Fast R-CNN, Faster R-CNN. How We Understand Scenes, From detected objects to an interpretation of the whole scene.
1

Read THRUN Chapters 2-3

Recursive estimation and Dynamic Bayesian Networks.
2

Review lecture: Recursive State Estimation

Bayes filter and its properties. See Recursive State Estimation.
3

Review lecture: Kalman Filters

Linear Gaussian models and the Kalman update equations. See Kalman Filters.
4

Watch videos

Introduction to State Estimation with HMM, Introducing Hidden Markov Models. The Bayes Filter, Implementing the Bayes filter algorithm. Discrete Bayes Filter Example, Discrete Bayes localization notebook. Continuous State Space and Kalman Filter, Localizing a drone under Gaussian assumptions. A Kalman Filter Example, Kalman localization notebook.
There is no lecture this week. You sit a take-home midterm instead, programming-oriented and covering weeks 1 to 5.
1

Read THRUN Chapters 5, 7, 9-10; CORKE Chapters 4, 6

Egomotion, velocity and odometry models and pose estimation in Chapters 5 and 7, then Simultaneous Localization and Mapping and Visual SLAM with monocular cameras in Chapters 9 and 10. Localization is covered here rather than as a week of its own.
2

Review lecture: SLAM

The SLAM problem and solution approaches. See SLAM.
3

Read the SLAM lecture page and watch videos

Read the full SLAM page and watch the three embedded videos: SLAM Overview Extended Kalman Filter (Cyrill Stachniss) EKF SLAM (Cyrill Stachniss)
1

Review lecture: Search Algorithms

Optimal planning under uncertainty, A*, D*, RRT*, PRM algorithms. See Search.
2

Review lecture: A* Algorithm

Heuristic search for path planning. See A*.
3

Watch videos

Introduction to Planning, Typical planning problems and PDDL. Planning Domain Definition Language, The constructs of PDDL. Forward Search Algorithms, Finding global planning solutions with forward search. The A* Algorithm, Using heuristics to guide forward search.
1

Review lecture: MDP Introduction

Sequential decisions, reward signals, and Bellman equations. See MDP Introduction.
2

Review lecture: Bellman Equations

Expectation and optimality backups. See Bellman Expectation.
3

Review lecture: Policy Improvement

From value functions to optimal policies. See Policy Improvement.
4

Watch videos

Introduction to MDPs - Part 1, Defining Markov Decision Processes. Introduction to MDPs - Part 2, Defining Markov Decision Processes. Bellman Expectation Equations - Part 1, Deriving the Bellman Expectation Equations. Bellman Expectation Equations - Part 2, Deriving the Bellman Expectation Equations. Bellman Optimal Value Functions, Deriving the Bellman Optimality Equations. Policy Iteration and Value Iteration, Using the Bellman Optimality Equations for optimal control. Policy Evaluation - Part 1, Evaluating a fixed policy with iterative updates. Policy Evaluation - Part 2, Convergence of policy evaluation and its role in policy iteration.
1

Review lecture: Reinforcement Learning

Model-free methods for robotic control policies. See Reinforcement Learning.
2

Review lecture: Temporal Difference Learning

TD methods and SARSA. See Temporal Difference.
3

Run the SARSA Gridworld notebook

Execute the SARSA Gridworld notebook.
4

Run the GERON Chapter 19 notebook

Work through the Reinforcement Learning notebook.
5

Watch videos

Monte Carlo Prediction, Estimating value functions from sampled episodes. Temporal Difference Learning, Bootstrapping value estimates from one-step transitions. Model-free Control, SARSA, Q-learning, and learning optimal policies without a model. Proximal Policy Optimization - Part 1, PPO foundations and clipped surrogate objective. Proximal Policy Optimization - Part 2, PPO implementation details and practical considerations.
1

Review lecture: Vision-Language Models

VLMs for human-robot collaboration. See VLM Introduction.
2

Review lecture: Imitation Learning

Learning from demonstrations for robotic manipulation. See Imitation Learning.
3

Watch videos

Introduction to Transformers, The transformer architecture and the simple attention mechanism. The Learnable Attention Mechanism, Implementing the scaled dot-product self attention mechanism. Multi-Head Self Attention, Using multiple attention heads to capture different aspects of input sequences.
1

Review lecture: VLA Agents

End-to-end Vision-Language-Action models for instruction parsing, perception, and action. See VLA Agents.
2

Watch videos

Coming soon, VLA models video lectures are in development.
1

Review lecture: Sim-to-Real Transfer

Training in simulation and deploying to real robots. See Sim-to-Real Transfer.
Edit this page on GitHub or file an issue.