Safe Model Predictive Control

In many real-world applications, robots are involved in uncertain, stochastic and dynamic environments, and required to satisfy some constraints such as collision avoidance, physical limits of the actuators, some user-defined preferences, etc. Within this context, “safety” can be defined as the stability of the control policy that satisfies the constraints considering also the uncertainties on them.

Thanks to model-based techniques, we can be explicitly aware of the safety requirements and optimize our control policy in such a way that the performance is not overly restricted while meeting the safety requirements.

Safe Model Predictive Control (Safe MPC) aims to ensure that a physical system’s safety constraints are satisfied with high probability. Our research is on extending constrained MPC methods to cope with probabilistic safety constraints. We further research modeling uncertainty of dynamics to ensure safe exploration when combined with safety constraints learned in simulation, and learning powerful data-efficient surrogate models for complex dynamics.

People involved

Project updates

Assignment on “Differential Dynamic Programming with Safety Constraints”

The goal of this assignment is to understand the constrained DDP with safety precautions and implement it on a real robot, e.g., Turtlebot 3 Waffle Pi. It is expected to perform the experiments in an engineered environment in which the positions of the robot and the obstacles will be measured by an external vision based system (motion capture system).

Master Thesis on “Constrained Differential Dynamic Programming”

In this thesis, an extensive investigation of constrained DDP methods will be performed and the major selected ones will be implemented in simulation environment for trajectory optimizations of different robots such as a simple point robot, 2D car-like robot, 3D quadrotor robot and cart-pole system. In this context, the methods will be compared in terms of convergence speed, computational complexity, sensitivity to initializations and parameter selections.

Master Thesis on “Trajectory Planning and Tracking for Autonomous Vehicles Using Model Predictive Control Incorporating Vehicle Dynamics”

In this thesis, an MPC based trajectory planning and tracking method will be developed for an autonomous vehicle in simulation. A high fidelity driving simulator will be employed to incorporate vehicle dynamics in MPC constraints. The developed control must guarantee collision-free, comfortable and efficient driving performance in complex urban driving environment.