Autonomous Systems

Beginner

Upon completing this course, students will be able to: - Demonstrate a Solid Foundation in Autonomous Navigation: Describe the principles of autonomous navigation, including different strategies such as waypoint navigation, visual navigation, and SLAM. Apply these strategies to various autonomous system applications. - Design and Implement Path Planning Algorithms: Design and implement various path planning algorithms, including grid-based, graph-based, and sampling-based methods; generate optimal paths for autonomous systems in complex environments. - Integrate Sensory Inputs for Navigation: Master data integration from multiple sensors such as LiDAR, GPS, IMU, and cameras and facilitate accurate localization, mapping, and navigation of autonomous systems using this data. - Apply SLAM Techniques: Understand and apply Simultaneous Localization and Mapping (SLAM) techniques; Enable autonomous systems to build and navigate maps of their environments. - Develop Obstacle Detection and Avoidance Mechanisms: Design real-time mechanisms for detecting and avoiding obstacles; ensure safe navigation of autonomous systems in dynamic environments. - Evaluate Navigation Strategies in Different Contexts: Assess the strengths and limitations of various navigation and path planning strategies; apply these strategies in different contexts, such as urban environments, indoor spaces, and off-road terrain.

None

- Introduction to Autonomous Systems: Overview of various autonomous systems, including ground vehicles, aerial drones, and maritime vehicles. Exploring the scope and challenges of autonomy. - Fundamentals of Path Planning: Introduction to concepts and algorithms used in path planning, such as grid-based, graph-based, and sampling-based methods. Discussion on A*, Dijkstra’s algorithm, RRT (Rapidly-exploring Random Tree), and their variations. - Localization and Mapping: Techniques for determining the system's position within its environment and creating maps. Discussion on SLAM (Simultaneous Localization and Mapping) and its variants, including visual SLAM and LiDAR-based approaches. - Navigation and Obstacle Avoidance: Strategies for autonomous navigation in dynamic environments, including static and moving obstacle avoidance. Overview of reactive and predictive models for safe navigation. - Machine Learning and AI in Autonomy: Exploration of the role of machine learning and artificial intelligence in enhancing the capabilities of autonomous systems, including decision-making, object detection, and adaptive path planning. - Control Systems for Autonomous Operation: Basics of control theory as applied to autonomous systems, including PID control, feedforward control, and state feedback control. Discussion on how these systems execute planned paths and maintain stability.

- Barfoot, T. D. (2024). State Estimation for Robotics. Cambridge University Press. ISBN: 978-1009299909. https://doi.org/10.1017/9781009299909 - LaValle, S. M. (2006). Planning Algorithms. Cambridge University Press. ISBN: 978-0521862059. - Siegwart, R., Nourbakhsh, I. R., & Scaramuzza, D. (2011). Introduction to Autonomous Mobile Robots (2nd ed.). The MIT Press. ISBN: 978-0262015356.

Exam

English

5

15

2.5

Presentation, group work, discussion, exercises

3

3_5

integrated lecture

Compulsory