INRIA Mobile Robots and Autonomous Vehicles MOOC

inria-41005S02-toc.txt

Mobile Robots and Autonomous Vehicles
by INRIA, via the FUN MOOC platform

https://www.france-universite-numerique-mooc.fr/courses/inria/41005S02/session02/about

Introduction	 
Course presentation	 
Guide: Learning Platform	 
Guide: Discussion Forums	 

Week 1: State of the art, basic principles & grand challenges - from February, 08	 
1.0. Introduction
1.1. Socio-economic context
1.2. Technological evolution of Robotics & State of the Art
1.3. New challenges for Robotics in Human Environments
1.4. Decisional & Control Architecture for Autonomous Mobile Robots & IV
1.5. Sensing technologies: Object Detection
1.6. Sensing technologies: Robot Control & HRI
1.7. Basic technologies for Navigation in Dynamic Human Environments
1.8. Intelligent Vehicles: Context & State of the Art
1.9. Intelligent Vehicles: Technical Challenges & Driving Skills
Course Documents	 

Week 2: Bayes & Kalman filters - from February, 15	 
Survey: profile and expectations	 
2.1. Basic concepts: robot configuration, localization and probabilistic framework	 
2.2. Characterization of proprioceptive and exteroceptive sensors
2.3. Wheel encoders for a differential drive vehicle
2.4. Sensor statistical models
2.5. Reminds on probability
2.6. The Bayes Filter
2.7. Grid Localization: an example in 1D
2.8. The Extended Kalman Filter (EKF)
Exercises Week 2	 
Course documents	 

Week 3: Extended Kalman filters - from February, 22	 
3.1. Examples for the Action in the EKF	 
3.2. Examples for the Perception in the EKF
3.3. The EKF is a weight mean
3.4. The use of the EKF in robotics
3.5. Simultaneous Localization and Mapping (SLAM)
3.6. Observability in robotics
3.7. Observability Rank Criterion
3.8. Applications of the Observability Rank Criterion
Exercises Week 3	 
Course Documents	 

Week 4: Perception & Situation Awareness & Decision Making - from February, 29	 
Survey: work time and satisfaction	 
4.1. Robot Perception for Dynamic environments - Outline & DP-Grids concept	 
4.2. Dynamic Probabilistic Grids ? Bayesian Occupancy Filter concept
4.3. Dynamic Probabilistic Grids ? Implementation approaches
4.4. Object level Perception functions (SLAM + DATMO)
4.5. Detection and Tracking of Mobile Objects ? Problem & Approaches
4.6. Detection and Tracking of Mobile Objects ? Model & Grid based approaches	 
4.7. Embedded Bayesian Perception & Short-term collision risk (DP-Grid level)
4.8. Situation Awareness ? Problem statement & Motion / Prediction Models
4.9. Situation Awareness ? Collision Risk Assessment & Decision (Object level)
Exercises Week 4	 
Course Documents	 

Week 5: Behavior modeling and learning (with examples and exercises in Python) - from March, 07	 
5.1. Introduction	 
5.2. E-M Clustering
5.3a. Learning typical trajectories 1/2
5.3b. Learning typical trajectories 2/2
5.4. Bayesian Filter inference: filtering, smoothing, prediction and recognition
5.5. Transforming typical trajectories in discrete time-state models
5.6. Recognizing, estimating and predicting human motion
5.7. Typical trajectories: drawbacks
5.8. Other approaches: Social Forces
5.9. Other approaches: Planning-based approaches
Course Conclusion	 
Course Documents	 
Survey: follow up on the Mooc and opinion