Chevron Left
Back to Motion Planning for Self-Driving Cars

Learner Reviews & Feedback for Motion Planning for Self-Driving Cars by University of Toronto

4.8
stars
453 ratings

About the Course

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)....

Top reviews

KN

Nov 30, 2020

If not online and self-paced, I would not have the courage to attempt this advanced-level Self-Driving Program. Thanks UoT and the instructors for offering such high-quality courses to the public. 👍😊

YD

Feb 4, 2020

The course is very good for the basic knowledge of self driving. There are a lot of good examples of different parts. I have learned a lot from it. Thank you for your excellent job!

Filter by:

76 - 85 of 85 Reviews for Motion Planning for Self-Driving Cars

By Brike

Mar 20, 2021

Excellent lesson!

I hope this course could provide some coding homework written in C++.

By 吕吉冬

May 8, 2019

Too many errors in slides and a little bit easy.

By Igor S

Nov 6, 2019

Good lectures, but badly prepared assignments.

By liviya v

Jan 1, 2021

goog course

By Dane R

Aug 29, 2020

The material covered was good, and the supplemental materials are always helpful to guide those that want to learn more (I am a huge fan of these references being provided, even if we have to hunt down a PDF).

I think this course was missing more coding exercises though. This is a deep subject, and a critical one in the AV world, so I'm very disappointed that there weren't more of these to illustrate how to solve some common motion planning problems.

The final project is also very weak. I understand that motion planning is very complex and involves a lot of math (making it difficult to create an assignment that isn't overwhelmingly difficult), but the final assignment is full of hand-holding, making already easy tasks trivial. Most of the interesting parts are already done for you, so I didn't have to think about motion planning at all. On top of that there is an error in the Coursera-provided code which students have pointed out a year ago, yet still exists. Fix this!

I think this course is worth doing if you are pursuing the Self Driving Car curriculum, and it has some solid information in it, but just don't expect to get rich coverage. The first 3 courses in the Self Driving Cars curriculum were much better.

By Shaun B

Aug 27, 2020

I wish there were more coding assignments in weeks 1-6. I also wish that the final assignment had more code for us to write. For example, collision_checker.py has <5 lines of code to be written.

By Patrick N

Jul 26, 2020

Final Test is a stupid reverse engineering and integration task without demand for deeper knowledge

By Isaac N (

Jun 21, 2020

TOO HIGHLEVEL

By Kasra D

May 13, 2021

This course is good for you if you already know the concepts and just want to review it. It's a terrible course if you don't know the concepts and want to learn from it. This is true for all courses in this specialization.

By Florian W

Nov 28, 2022

The final assignment is heavily outdated and incompatible with current Linux-based operating systems. It relies on heavily outdated versions of python and other pip packages. An absolute pain.