Rik Timmers

About

Rik Timmers is a researcher focused on advancing autonomous robotic systems through the integration of deep learning, reinforcement learning, and sensor-efficient navigation. His work addresses fundamental challenges in how robots perceive, localize, and interact with their environments, particularly in indoor settings. Timmers’ most influential contribution is his 2015 paper on indoor localization using denoising autoencoders and semi-supervised learning in 3D simulated environments, which has garnered 49 citations. This work proposed a novel approach to reduce reliance on expensive depth sensors and heavy computational hardware by leveraging neural networks for spatial mapping and localization. He further explored goal-directed behavior in his 2021 study on two-stage visual navigation using deep neural networks and multi-goal reinforcement learning (13 citations), and investigated robotic manipulation in his 2018 work on learning to grasp objects with reinforcement learning. Timmers’ research is particularly relevant for domestic service robots, where efficient, low-cost perception and adaptive control are critical. His contributions demonstrate a clear trajectory toward more intelligent, autonomous systems capable of complex tasks in real-world environments.

Research Focus

Key Achievements

Top Papers

1. 1
   Indoor localization by denoising autoencoders and semi-supervised learning in 3D simulated environment

   49 citations · 2015
2. 2
   Two-stage visual navigation by deep neural networks and multi-goal reinforcement learning

   13 citations · 2021
3. 3
   Learning to Grasp Objects with Reinforcement Learning

   2 citations · 2018

Key Collaborators

Contact & Links