Mobile Perception Systems Lab

The Mobile Perception Systems Lab researches methods in Artificial Intelligence that allow mobile autonomous systems to perceive their environment. Our long-term goal is to realize AI that can anticipate on future events in highly dynamic and complex environments. We always validate our AI methods 'in the loop', meaning in the context of challenging real-world applications, mainly from the industry domains of automotive, transportation, and logistics.

MPS is part of the Signal Processing Systems group and we work closely with the Embedded Systems group, the Dynamics and Control group, the Control Systems Technology group, and the TU/e-wide Strategic Area for Smart Mobility.

Perception Through Anticipation

The MPS lab specializes in the following AI methods: deep learning, multi-modal computer vision, and simultaneous localization and mapping. These are key enabling technologies that allow mobile sensor platforms to perceive and interpret their environments from past and current sensory data, in essence estimating a dynamic digital world-model in real-time. In coming years, we aim to make a step in the direction of spatio-temporal reasoning engines that allow mobile sensor platforms to predict possible future events and thereby achieve anticipation capabilities. Currently, the lack of anticipation capabilities, is a key bottleneck in deploying mobile autonomous systems in complex and dynamic environments, such as self-driving cars in crowded inner cities. We firmly believe that in order to advance AI and its applications, both an inter-disciplinary approach and a strong cooperation with industry are required. Hence, we are involved in many cross-disciplinary European projects and initiatives, such as the International Connected and Automated Driving Institute (https://icadi.net), and we recently started the company AI In Motion to bring our technologies to the market (https://aiim.ai). 

News

January 26, 2023
Advances in Perception for Automated Mobile Systems
Chenyang Lu defended his PhD thesis at the department of Electrical Engineering on January 25th.
Read more
January 10, 2023
ROBUST AI program receives additional €25 million in funding from Dutch Research Council
ROBUST focuses primarily on the development of trustworthy AI technology for the resolution of socially relevant issues, such as those in healthcare, logistics,...
Read more
More news
Autonomous traffic insight
November 4, 2021
Two more labs at TU/e join ranks of Dutch AI network
January 26, 2021

Example project: iCAVE

i-CAVE (integrated Cooperative Automated VEhicles) examines all the key aspects of the self-driving car. The program’s participants will co-develop vehicles that are able to drive autonomously on closed roads and cooperatively on public roads. The researchers also focus thereby on the development of the requisite sensors like cameras and radar as well as the logistics involved and the human-car interaction. Participants in i-CAVE include companies like DAF, NXP and Ford as well as parties such as ANWB (the Dutch automobile association), TNO, AutomotiveNL and the Ministry of Infrastructure and the Environment. Read more

Meet some of our Researchers

Chenyang Lu

Doctoral Candidate

Fabrizio Piva

Postdoc

Ariyan Bighashdel

Associate Professor

Gijs Dubbelman

Postdoc

Daan de Geus

Project Manager

Jos den Ouden

Recent Publications

Our most recent peer reviewed publications

AIIM (AI in Motion)

Rethinking and redesigning possibilities by adding intelligence onto machine perception and localization to steer autonomous vehicles and robots within challenging dynamic environments.

Originating from the TU Eindhoven Mobile Perception Systems Lab, AIIM focusses on capturing high precision insights through autonomous vehicles in both indoor and outdoor environments. These learnings can be applied to create agile solutions for the Agricultural, Robotics, Vision, and IoT industries. Read more

Contact