Survey article on POMDPs in robotics in IEEE T-RO
Partially observable Markov decision processes (POMDPs) are a mathematical model for decision-making under uncertainty. Among other things, POMDPs can help r...
2022
Python API for Dec-POMDP problems in the .dpomdp format
Decentralized POMDPs are a popular mathematical framework for multiagent sequential decision-making under uncertainty. The .dpomdp file format for describing...
2021
Object pose estimation with on-line data synthesis using point clouds at ICRA 2021
With Ge Gao, Xiaolin Hu, Jianwei Zhang, and Simone Frintrop, we propose an augmented autoencoder based approach for estimating the translation and rotation o...
Interview on Data Skeptic podcast
I recently appeared on the Data Skeptic podcast to talk about my research into decentralized information gathering and multi-agent active perception. You can...
2020
Talk on pose estimation and audio-visual paper at ICPR 2020
With Ge Gao, we are giving a workshop talk at the ``Perception and Modelling for Manipulation of Objects’’ workshop organized at the 25th International Conf...
New results on multi-agent active perception at NeurIPS 2020
We have a new paper entitled “Multi-agent active perception with prediction rewards” at the 34th Conference on Neural Information Processing Systems (NeurIPS...
Multi-robot next-best-view planning
In this post, I give an overview of my recent paper (Lauri et al., 2020) on multi-robot next-best-view planning.
Active perception and decentralized decision-making
In this post, I give an overview of my recent research on multi-agent active perception, published in the two recent papers (Lauri et al., 2020; Lauri et al....
Website started
Today, the first version of the website is up. I used jekyll, along with the minimal-mistakes theme and jekyll-scholar plugin for citations.