Motion Planning for Self-Driving Cars
Welcome to Motion Planning for Self-Driving Cars, the fourth course in University of Toronto’s Self-Driving Cars Specialization. This course will introduce you to the main planning tasks in autonomous driving, including mission planning, behavior planning and local planning. By the end of this course, you will be able to find the shortest path over a graph or road network using Dijkstra's and the A* algorithm, use finite state machines to select safe behaviors to execute, and design optimal, smooth paths and velocity profiles to navigate safely around obstacles while obeying traffic laws.
Monthly Subscription Starting at AED 99 + VAT
- Level Expert
- المدة 32 ساعات hours
- الطبع بواسطة University of Toronto
-
Offered by
عن
Welcome to Motion Planning for Self-Driving Cars, the fourth course in University of Toronto’s Self-Driving Cars Specialization. This course will introduce you to the main planning tasks in autonomous driving, including mission planning, behavior planning and local planning. By the end of this course, you will be able to find the shortest path over a graph or road network using Dijkstra's and the A* algorithm, use finite state machines to select safe behaviors to execute, and design optimal, smooth paths and velocity profiles to navigate safely around obstacles while obeying traffic laws. You'll also build occupancy grid maps of static elements in the environment and learn how to use them for efficient collision checking. This course will give you the ability to construct a full self-driving planning solution, to take you from home to work while behaving like a typical driving and keeping the vehicle safe at all times. For the final project in this course, you will implement a hierarchical motion planner to navigate through a sequence of scenarios in the CARLA simulator, including avoiding a vehicle parked in your lane, following a lead vehicle and safely navigating an intersection. You'll face real-world randomness and need to work to ensure your solution is robust to changes in the environment. This is an intermediate course, intended for learners with some background in robotics, and it builds on the models and controllers devised in Course 1 of this specialization. To succeed in this course, you should have programming experience in Python 3.0, and familiarity with Linear Algebra (matrices, vectors, matrix multiplication, rank, Eigenvalues and vectors and inverses) and calculus (ordinary differential equations, integration).الوحدات
Course Introduction
-
4
Videos
-
3
Readings
-
1
Discussion
1
Discussions
- Get to Know Your Classmates
4
Videos
- Welcome to the Self-Driving Cars Specialization!
- Welcome to the Course
- Meet the Instructor, Steven Waslander
- Meet the Instructor, Jonathan Kelly
3
Readings
- Course Readings
- How to Use Discussion Forums
- How to Use Supplementary Readings in This Course
The Planning Problem
-
4
Videos
-
1
Readings
4
Videos
- Lesson 1: Driving Missions, Scenarios, and Behaviour
- Lesson 2: Motion Planning Constraints
- Lesson 3: Objective Functions for Autonomous Driving
- Lesson 4: Hierarchical Motion Planning
1
Readings
- Module 1 Supplementary Reading
Week 1 Graded Assignment
-
1
Assignment
1
Assignment
- Module 1 Graded Quiz
Mapping for Planning
-
5
Videos
-
1
Readings
5
Videos
- Lesson 1: Occupancy Grids
- Lesson 2: Populating Occupancy Grids from LIDAR Scan Data (Part 1)
- Lesson 2: Populating Occupancy Grids from LIDAR Scan Data (Part 2)
- Lesson 3: Occupancy Grid Updates for Self-Driving Cars
- Lesson 4: High Definition Road Maps
1
Readings
- Module 2 Supplementary Reading
Module 2 Weekly Assignment: Occupancy Grid Generation
-
1
Lab
-
1
Programming
- Occupancy Grid Generation
1
Labs
- Occupancy Grid Generation
Mission Planning in Driving Environments
-
3
Videos
-
1
Readings
3
Videos
- Lesson 1: Creating a Road Network Graph
- Lesson 2: Dijkstra's Shortest Path Search
- Lesson 3: A* Shortest Path Search
1
Readings
- Module 3 Supplementary Reading
Module 3 Weekly Assignment
-
1
Lab
-
1
Assignment
1
Assignment
- Module 3 Graded Quiz
1
Labs
- Practice Assignment: Road Network Shortest Path Search
Dynamic Object Interactions
-
3
Videos
-
1
Readings
3
Videos
- Lesson 1: Motion Prediction
- Lesson 2: Map-Aware Motion Prediction
- Lesson 3: Time to Collision
1
Readings
- Module 4 Supplementary Reading
Module 4 Weekly Assignment
-
1
Assignment
1
Assignment
- Module 4 Graded Quiz
Principles of Behaviour Planning
-
5
Videos
-
1
Readings
5
Videos
- Lesson 1: Behaviour Planning
- Lesson 2: Handling an Intersection Scenario Without Dynamic Objects
- Lesson 3: Handling an Intersection Scenario with Dynamic Objects
- Lesson 4: Handling Multiple Scenarios
- Lesson 5: Advanced Methods for Behaviour Planning
1
Readings
- Module 5 Supplementary Reading
Module 5 Weekly Assignment
-
1
Assignment
1
Assignment
- Module 5 Graded Quiz
Reactive Planning in Static Environments
-
4
Videos
-
1
Readings
4
Videos
- Lesson 1: Trajectory Propagation
- Lesson 2: Collision Checking
- Lesson 3: Trajectory Rollout Algorithm
- Lesson 4: Dynamic Windowing
1
Readings
- Module 6 Supplementary Reading
Module 6 Weekly Assignment
-
1
Assignment
1
Assignment
- Module 6 Graded Quiz
Smooth Local Planning
-
5
Videos
-
1
Readings
5
Videos
- Lesson 1: Parametric Curves
- Lesson 2: Path Planning Optimization
- Lesson 3: Optimization in Python
- Lesson 4: Conformal Lattice Planning
- Lesson 5: Velocity Profile Generation
1
Readings
- Module 7 Supplementary Reading
Final Project
-
2
Videos
-
1
Readings
-
1
Programming
- Course 4 Final Project
2
Videos
- Final Project Overview
- Final Project Solution [LOCKED]
1
Readings
- CARLA Installation Guide
Congratulations!
-
2
Videos
2
Videos
- Congratulations for completing the course!
- Congratulations on Completing the Specialization!
Auto Summary
Unlock the future of autonomous driving with "Motion Planning for Self-Driving Cars," a cutting-edge course offered by the University of Toronto as part of their Self-Driving Cars Specialization. Dive into the essential planning tasks of autonomous vehicles, from mission planning to local execution, and master techniques such as Dijkstra's and A* algorithms for shortest pathfinding, finite state machines for safe behavior selection, and optimal path design for navigating complex environments. Guided by expert instructors, this course offers a deep dive into constructing occupancy grid maps for collision checking and developing a comprehensive self-driving planning solution. Test your skills with a final project in the CARLA simulator, where you will implement a hierarchical motion planner to tackle real-world driving scenarios. Designed for intermediate learners with a background in robotics, the course requires proficiency in Python 3.0, Linear Algebra, and calculus. With a duration of 1920 minutes, you can choose between Starter and Professional subscription options to fit your learning needs. Join now to become an expert in the dynamic field of autonomous vehicle motion planning and contribute to the future of transportation technology.
Steven Waslander
Jonathan Kelly