News

Congrats to Takuma Yoneda and Xuefeng Liu for having their paper on interleaving reinforcement and imitation learning accepted as a spotlight at ICLR 2024

We hosted the 2024 Midwest Robotics Workshop, which brought together 150+ students, postdocs, faculty, and industry researchers from the midwest (broadly interpreted) to network and showcase their work.

Congratulations to Han Shao and Lee Cohen on their NeurIPS 2023 paper on preference elicitation for personalized multi-objective decision making.

Together with Greg Shakhnarovich and our collaborators at TRI, we are organizing a Workshop on the Frontiers of Monocular 3D Perception: Geometric Foundation Models at ICCV 2023 in Paris. As the third edition of our workshop series, this event focuses on how we might use geometry to learn and apply ``foundation models’’ in the context of 3D perception.

Andrea Daniele successfully defended his PhD thesis on ``Accessible Interfaces for the Development and Deployment of Robotic Platforms’’!!! He will be leaving us for greener yellower pastures as CTO of Duckietown.

Together with Andrea Censi, Jacopo Tani, Liam Paull, and Andrea Daniele, we are kicking off the new edition of our Self-Driving Cars with Duckietown MOOC.

Congrats to Chip Schaff for successfully defending his PhD thesis on ``Neural Approaches to Co-optimization in Robotics’’!!!

Congratulations to Jiading Fang for having his paper on learning consistent multi-view scene representations accepted at ECCV!

Congratulations to Chip Schaff for having his paper on co-optimization of soft robots accepted at RSS!

Takuma Yoneda’s paper on learning invariant representations for RL was accepted at RSS. Congrats!

Congratulations to Jiading Fang for having his paper on self-supervised camera calibration accepted at ICRA!

TTIC released an article about Keziah as part of the Student Highlights series.

TTIC released an article about Chip as part of the Student Highlights series.

Together with Andrea Censi, Jacopo Tani, and Liam Paull, we are organizing AI-DO 2021, which will take part this December as part of NeurIPS 2021. AI-DO provides excellent opportunities to develop and benchmark ML and AI approaches to embodied intelligence and is open to anyone.

We are organizing the IROS 2021 Workshop on Evaluating the Broader Impacts of Self-Driving Cars, featuring a great lineup of speakers with expertise in legal, ethical, and safety matters pertaining to self-driving.

Together with folks at TU Darmstadt, the University of Washington, and the Max Planck Institute, we explored our different approaches to the Real Robot Challenge. The corresponding code and paper are available on the project page.

We took first place in the Real Robot Challenge! Congrats to Chip Schaff, Takuma Yoneda, and Takahiro Maeda.

Together with Andrea Censi, Jacopo Tani, and Liam Paull, we are teaching the first robotics and AI MOOC with scale-model self-driving cars through the edX platform.

We are organizing the Workshop on Benchmarking Progress in Autonomous Driving at IROS 2020 and soliciting position papers. Please consider submitting.

Congratulations to Tri on having his multigrid neural memory paper accepted to ICML 2020.

Congrats to Chip for his RSS 2020 paper on residual learning for model-free shared autonomy.

We are co-organizing the Workshop on Frontiers of Monocular 3D Perception at CVPR 2020.

We are co-organizing the Workshop on Benchmarking Progress in Autonomous Driving at ICRA 2020. Please consider participating.

We had the fortune to participate in a NASA-funded research cruise exploring the Kolumbo submarine volcano, which was covered by various news media, including Wired and the British daily i newspaper, among others.

Congrats to Falcon on our NeurIPS 2019 paper that proposes a new complexity measure for MDPs.

We have introduced DIODE, a dataset of high-resolution color images with accurate depth measurements for diverse indoor and outdoor scenes.

Congratulations to Falcon Dai for being nominated for Best Paper at ACL 2019!

Congrats to David Yunis for being awarded an NSF Graduate Research Fellowship!

Jon Michaux was awarded a prestigious OpenAI Scholars position. Congrats!

We are organizing the Workshop on Models and Representations for Natural Human-Robot Communication at RSS.

Congrats to Chip and Andrea for winnning the best talk and best poster awards at the 2017 TTIC Student Workshop!

Congrats to Andrea on our paper on multiview articulation learning, which will appear at ISRR.

Thanks to TTIC’s support, we will be teaching a hands-on class on self-driving vehicles in the Autumn 2017 quarter, as a follow-on to the 2016 “Duckietown” course at MIT.

We are organizing a AAAI Fall Symposium on Natural Communication for Human-Robot Collaboration, and are soliciting submissions that describe current and ongoing work on human-robot communication.

Congrats to Chip and David on our paper on joint neural optimization over beacon allocation and inference, which will appear at IROS.

Our paper that proposes a language model for monologue (i.e., multi-sentence) understanding will appear at RO-MAN.

NVIDIA Developer News highlighted our work on satellite image-based localization, which will appear at ICRA 2017.

Andrea was interviewed by CBS 2 Chicago about our lab’s involvement in National Robotics Week at the Museum of Science and Industry. The video is available here (Note: Andrea is a student at TTIC, not the University of Chicago, as reported).

Our paper on satellite image-based localization was accepted at ICRA.

Our paper route instruction generation will appear at HRI.

Our paper on attention-based dialogue models will appear at AAAI.

Thomas Howard and Matthew Walter are hosting the second Workshop on Model Learning for Human-Robot Communication at RSS.

Our paper on generating natural language descriptions of databases will appear at NAACL 2016.

TTI-Chicago is hosting the first annual Midwest Robotics Workshop. We encourage robotics researchers in and around the Midwestern US to participate!

We were awarded an NVIDIA Titan X GPU for our paper at the NIPS 2015 Multimodal Machine Learning workshop!

Our neural route instruction paper will appear at AAAI 2016.

We will be presenting three papers at the NIPS Multimodal Machine Learning and Transfer and Multi-task Learning workshops in December.

Matthew Walter will present our dialog paper at IROS in Hamburg.

Our papers on dialog for semantic mapping and efficient language understanding will appear at IROS 2015.

Thomas Howard and Matthew Walter are hosting an RSS 2015 Workshop on Model Learning for Human-Robot Communication.

Our paper on language understanding in unknown environments was accepted at ICRA.