direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Logo der TU Berlin

Inhalt des Dokuments

Dynamic Learning and Control

From Fachgebiet Regelungssysteme TU Berlin

Jump to: navigation, search

These research activities are dedicated to the development of new methods for Learning and Control in a large range of applications that require online adaptation and decision making in real time. By combining novel machine learning approaches with well-founded systems and control theory, we aim to provide methods that overcome trade-offs between agility and accuracy on the one hand and resilience and explainability on the other hand.

Most research projects are concerned with specific application systems and with leveraging the advantages of the newly devised methods to overcome real-world challenges in autonomous aerial and ground vehicles, collaborative robotic systems and P4 medicine solutions.

Iterative Learning Control for Variable-Pass-Length Systems

Teaser_Thumb

A number of potential applications of iterative learning control do not fulfill the standard assumption of a uniform pass length, i.e. a constant trial duration. We extend the available methods to the case in which the pass length varies arbitrarlily and unpredictably from trial to trial.more

Adaptive Drop Foot Neuroprostheses

Teaser_Thumb

Neuromuscular stimulation is used in the rehabilitation of stroke patients to support weak dorsiflexion of the foot. Since FES dynamics are highly individual and time-varying, the use of closed-loop control methods is required to generate precise motions. For this particular application, we are developing control schemes inspired by Iterative Learning Control.more

Noninvasive Blood Pressure Tracking

Teaser_Thumb

A noninvasive continuous blood pressure measurement technique that has been developed lately requires precise control of the blood flow through a superficial artery. This project is concerned with the design and evaluation of advanced controllers that are precise enough to enable the indirect measurement principle.more

Trajectory Tracking on a Gantry Crane

Teaser_Thumb

In this project, we apply Iterative Learning Control to trajectory tracking on a lab-scaled gantry crane. However, in constrast to previous work, we assume that the load is only allowed to move in the close proximity of the reference trajectory. Since these output constraints lead to disrupted trials, the pass length in this ILC system is not constant.more

4DoF Gait Neuroprostheses

Teaser_Thumb

In order to support knee flexion/extension as well as foot dorsiflexion, plantarflexion and eversion, we develop multichannel gait neuroprostheses. The stimulation intensities are adjusted from stride to stride based on inertial sensor measurements and a decentralized iterative learning control scheme.more

Learning Vector Fields for Arm Rehabilitation

Teaser_Thumb

We consider the combination of a cable-driven arm robotic system and neuromuscular stimulation for upper limb rehabilitation. In order to support motions of the patient's arm in the horizontal plane, we adjust the stimulation intensities using iterative learning vector fields.more

Learning to Swing-Up a Pendulum

Teaser_Thumb

In the presence of large measurement delays, pendulum swing-up cannot be achieved by immediate feedback. However, learning control methods can be used to swing up the pendulum in a few trials.more

Development and Iterative Learning Control of a Two-Wheeled Inverted-Pendulum-Robot

Teaser_Thumb

The goal of this project is the development and iterative learning control of a two-wheeled inverted-pendulum robot (TWIPR), which is meant to intelligently interact with its environment.more

Collective Learning Phenomena in Swarms of Robotic Agents

Teaser_Thumb

The goal of this project is to study collective learning phenomena in a swarm of two-wheeled inverted pendulum robots (TWIPR) that use a combination of learning control methods and distributed control methods to accomplish a complex taks.more

Overcoming Output-Constraints in Iterative Learning Control Systems by Reference Adaptation

Teaser_Thumb

The goal of this project is the development of a reference adaptation scheme for iterative learning control systems to guarantee compliance with output constraints.more

Recommend this page