Motion Planning for Self-Driving Cars

Go to Course: https://www.coursera.org/learn/motion-planning-self-driving-cars

Introduction

### Course Review: Motion Planning for Self-Driving Cars #### Overview: If you’re passionate about autonomous vehicles and want to delve into the intricacies of how they navigate the world around them, the **Motion Planning for Self-Driving Cars** course offered by the University of Toronto on Coursera is an excellent choice. As the fourth installment in the Self-Driving Cars Specialization, this course provides a comprehensive overview of the various planning tasks essential for autonomous driving, including mission planning, behavior planning, and local planning. #### Course Structure: The course consists of seven modules, each building on the concepts introduced in the previous ones, making it easy to follow even for those new to the field. Here’s a brief rundown of the modules: 1. **Welcome to Course 4: Motion Planning for Self-Driving Cars** - An introductory module that sets the stage for the learning ahead. 2. **Module 1: The Planning Problem** - This module dives into the complexities of motion planning in self-driving cars. It covers the key scenarios encountered during driving and introduces a hierarchical optimization problem to help structure the planning process. 3. **Module 2: Mapping for Planning** - Focused on occupancy grids, this module teaches how to represent driving environments and efficiently map them using 2D and 3D LIDAR scans. 4. **Module 3: Mission Planning in Driving Environments** - Here, learners explore graph-based approaches for navigating between locations in the driving environment, utilizing algorithms such as Dijkstra’s and A* for finding the shortest paths. 5. **Module 4: Dynamic Object Interactions** - This module emphasizes understanding dynamic obstacles and assessing potential collisions with vehicles and pedestrians, a critical aspect of making autonomous driving safe. 6. **Module 5: Principles of Behaviour Planning** - Students will learn to develop rule-based systems for high-level decision-making in driving scenarios, like lane changes and navigating intersections. 7. **Module 6: Reactive Planning in Static Environments** - This module focuses on creating locally feasible paths that are collision-free while reaching targets identified in a map, an essential skill for real-time decision making. 8. **Module 7: Putting it all together - Smooth Local Planning** - The final module emphasizes the optimization of paths using parameterized curves, allowing learners to design smooth trajectories. #### What You Will Learn: By the end of this course, you will gain the following skills: - Ability to navigate graphs and road networks effectively using established algorithms like Dijkstra's and A*. - Proficiency in defining and managing behaviors using finite state machines, ensuring that the vehicle safely interacts with complex environments. - Competence in the principles of behavior planning, and the ability to create systems that govern driving decisions. - Hands-on experience with reactive planning techniques for real-time autonomous navigation. #### Target Audience: This course is ideal for students and professionals interested in computer science, robotics, and machine learning, particularly those looking to specialize in autonomous vehicles. A foundational understanding of algorithms and basic knowledge of robotics will be beneficial, though the course is structured to help learners build their skills progressively. #### Recommendation: I highly recommend the **Motion Planning for Self-Driving Cars** course for anyone looking to deepen their understanding of the algorithms and systems that underpin autonomous driving technologies. The course is well-structured, engaging, and packed with practical knowledge that can be applied to real-world scenarios. Moreover, the instructors are knowledgeable in their fields, enriching the experience with their expertise. Completing this course will not only enhance your resume but also empower you with the skills needed to contribute to one of the most exciting fields in technology today. Whether you wish to pursue a career in the self-driving vehicle industry or enhance your current skill set, this course is a significant step in that direction. Embrace the future of transportation—enroll today!

Syllabus

Welcome to Course 4: Motion Planning for Self-Driving Cars

This module introduces the motion planning course, as well as some supplementary materials.

This module introduces the richness and challenges of the self-driving motion planning problem, demonstrating a working example that will be built toward throughout this course. The focus will be on defining the primary scenarios encountered in driving, types of loss functions and constraints that affect planning, as well as a common decomposition of the planning problem into behaviour and trajectory planning subproblems. This module introduces a generic, hierarchical motion planning optimization formulation that is further expanded and implemented throughout the subsequent modules.

The occupancy grid is a discretization of space into fixed-sized cells, each of which contains a probability that it is occupied. It is a basic data structure used throughout robotics and an alternative to storing full point clouds. This module introduces the occupancy grid and reviews the space and computation requirements of the data structure. In many cases, a 2D occupancy grid is sufficient; learners will examine ways to efficiently compress and filter 3D LIDAR scans to form 2D maps.

This module develops the concepts of shortest path search on graphs in order to find a sequence of road segments in a driving map that will navigate a vehicle from a current location to a destination. The modules covers the definition of a roadmap graph with road segments, intersections and travel times, and presents Dijkstra’s and A* search for identification of the shortest path across the road network.

This module introduces dynamic obstacles into the behaviour planning problem, and presents learners with the tools to assess the time to collision of vehicles and pedestrians in the environment.

This module develops a basic rule-based behaviour planning system, which performs high level decision making of driving behaviours such as lane changes, passing of parked cars and progress through intersections. The module defines a consistent set of rules that are evaluated to select preferred vehicle behaviours that restrict the set of possible paths and speed profiles to be explored in lower level planning.

A reactive planner takes local information available within a sensor footprint and a global objective defined in a map coordinate frame to identify a locally feasible path to follow that is collision free and makes progress to a goal. In this module, learners will develop a trajectory rollout and dynamic window planner, which enables path finding in arbitrary static 2D environments. The limits of the approach for true self-driving will also be discussed.

Parameterized curves are widely used to define paths through the environment for self-driving. This module introduces continuous curve path optimization as a two point boundary value problem which minimized deviation from a desired path while satisfying curvature constraints.