Online Autonomous systems tutor

Course Learning Outcomes CLO1 : Analyse the theoretical underpinnings of Bayesian Estimation and demonstrate advanced proficiency in implementing the Kalman Filter to address diverse engineering challenges. CLO2 : Apply critical analysis to optimization techniques, demonstrating the ability to strategically employ them in solving complex engineering problems. CLO3 : Evaluate and integrate Sensor Data Fusion methodologies for vehicle localization and other engineering challenges, demonstrating a mastery of their application. CLO4 : Design and implement software solutions for solving complex engineering problems, critically assess the performance of applied approaches, and gain experience with typical sensors utilized in Field Robotics and Autonomous Systems. Course Learning Outcomes Assessment Item CLO1 : Analyse the theoretical underpinnings of Bayesian Estimation and demonstrate advanced proficiency in implementing the Kalman Filter to address diverse engineering challenges. • Assignment 2: Sensor Data Fusion, via EKF and via Optimization. • Tests • Final Exam CLO2 : Apply critical analysis to optimization techniques, demonstrating the ability to strategically employ them in solving complex engineering problems. • Assignment 1. Sensor data fusion, via deterministic approach. • Assignment 2: Sensor Data Fusion, via EKF and via Optimization. • Tests • Final Exam CLO3 : Evaluate and integrate Sensor Data Fusion methodologies for vehicle localization and other engineering challenges, demonstrating a mastery of their application. • Assignment 1. Sensor data fusion, via deterministic approach. • Assignment 2: Sensor Data Fusion, via EKF and via Optimization. • Tests • Final Exam CLO4 : Design and implement software solutions for solving complex engineering problems, critically assess the performance of applied approaches, and gain experience with typical sensors utilized in Field Robotics and Autonomous Systems. • Assignment 1. Sensor data fusion, via deterministic approach. • Assignment 2: Sensor Data Fusion, via EKF and via Optimization. Teaching Week/Module Activity Type Content Week 1 : 12 February - 18 February Lecture Review of necessary concepts : State space models. LTI, Linear Time variant, and nonlinear cases. MIMO systems. State observers. Discrete time approximation for continuous time state equations. Coordinate frames / transformations. Programming using Matlab (Examples). Tut-Lab Solving problems related to state space modelling , to programming, and to coordinate frames. Week 2 : 19 February - 25 February Lecture Kinematic Models. Sensors: 2D LiDAR. IMU. Dead reckoning. Explanation Project 1. Tut-Lab Solving problems related to models. Programming. First steps working on Project 1. Assessment Minor quiz (10m). Week 3 : 26 February - 3 March Lecture Using Optimization. Map-based localization. Tut-Lab Solving problems by applying optimization. Programming. Working on Project 1. Week 4 : 4 March - 10 March Lecture Review of Statistics, including concepts such as random variables (RV), probability density function (PDF), joint PDF, marginal PDF, conditional PDF, statistical dependence, white noise, and Bayes' Rule. Introduction to Bayesian Estimation. Tut-Lab Hints about programming. Working on Project 1. Assessment Minor quiz (15m). Week 5 : 11 March - 17 March Lecture Topics include Gaussian random variables (RVs), handling high-dimensional cases, covariance matrix, Bayesian estimation under Gaussian assumption, Kalman Filter (KF), Extended Kalman Filter (EKF), and practical examples of application. Tut-Lab Solving Problems. Working on Project 1. Assessment Submission Project 1, Friday, 23:55. Week 6 : 18 March - 24 March Tut-Lab Optional: Students do have access to the Lab for working and consulting teaching staff. Week 7 : 25 March - 31 March Lecture State augmentation. Estimating parameters in real-time via EKF. Discussion about Project 2. Tut-Lab Solving problems related to estimating parameters in real-time via EKF. Working on Project 2. Presentation Students demonstrate their previously submitted project 1. Week 8 : 1 April - 7 April Laboratory Alternative optimization approaches. PSO. GA. Tut-Lab Working on Project 2. Assessment Major quiz. 30m. Thu 17:00 - 17:30 Week 9 : 8 April - 14 April Lecture Dynamic Programming. Dijkstra’s approach. Tut-Lab Working on Project 2. Assessment Submission Project 2, Friday, 23:55. Week 10 : 15 April - 21 April Lecture Revision. Discussion about Exam. Contingency time. Tut-Lab Students demonstrate their previously submitted project 2.

Level: Bachelors/Undergraduate

Gender Preference: None

Meeting options:
Available online - via skype etc.

---