UT Austin's Autonomous Mobile Robotics Laboratory

Led by professor Joydeep Biswas, AMRL performs research in robotics to continually make robots more autonomous, accurate and robust in unstructured environments

[Amanda Adkins @Amanda_A_Adkins]

Do you need a dense map to localize your robot over long-term deployments? We don’t think so!

Want to know how? If you're at #IROS2024, come checkout my presentation on "ObVi-SLAM: Long-Term Object-Visual SLAM" at 10:15 (October 17) in Room 1.

[Arthur King Zhang @ArthurKZhang]

I am thrilled to announce that UT CODa has been accepted at #IeeeTro24! Thank you to all of my collaborators at @Joydeepb_robots @amrl_ut who helped make this work possible. We are also excited to share the release of CODa version 2. More on CODa v2 in this🧵

[Joydeep Biswas @Joydeepb_robots]

Thrilled to share one of our projects at #NVIDIA this Summer - enabling long-horizon open-world perception and recall for mobile robots!
Fantastic work by @_abraranwar over his internship, jointly with Yan Chang, John Welsh, and @SohaPouya
https://t.co/nQn3iywCEz

[Haresh Karnan @KarnanHaresh]

Attending #CoRL2023 in Atlanta? come say hi 👋 at our poster on November 8th (Wed) 12-12:45pm in Mobility.

Joint work w/ amazing collaborators ElvinYang, DanielFarkash, @GarrettWarnell @PeterStone_TX @Joydeepb_robots

@amrl_ut @utlarg @UTAustin @texas_robotics @corl_conf

[Haresh Karnan @KarnanHaresh]

Introducing STERLING 💫: "Self-Supervised Terrain Representation Learning from Unconstrained Robot Experience" 💫 to be presented at CoRL 2023 in Atlanta! 😀

Project Page 🌎: https://t.co/TtNbgZTnjR

Paper 🗞️: https://t.co/12YxBOnFVG

A thread 🧵

[Joydeep Biswas @Joydeepb_robots]

Interested in urban-scale autonomous mobile robots? UT CODa is for you!

1.3M 3D BB annotations
53 object classes
204 M annotated points w/ 24 terrain classes
Globally consistent poses

Pre-trained models for 16, 32, 64, 128-channel LIDAR
https://t.co/yeZ3Uke4BE

[Arthur King Zhang @ArthurKZhang]

Context-aware navigation requires object/terrain-level understanding - in support of this, we are thrilled to release CODa, the largest multi-class, multi-modal urban robotics dataset to date.
https://t.co/z0I9giJyUQ

Work done with a fantastic team from @amrl_ut!
A short 🧵, 1/7

[Rohan Chandra @rohanchandra30]

What do we really need for social navigation?🤖

Deep RL? No❌
Imitation learning? No❌
LLMs? No❌

📊Turns out for over 80% of the time, classical methods >> learning-based solutions!

In new work, we rethink social navigation. Thread🧶

[Multi-Robot and Multi-Agent Systems Symposium 2023 @MultiRobotSys]

For this year's symposium, we received 85 submissions, of which 30 were accepted to be presented in December! Congrats to all the authors!🎉

We have also release the call for extended abstracts: https://t.co/31n6XOtrwB

Deadline: Oct. 10, 2023

[Texas Robotics @texas_robotics]

Check out this amazing work from Rohan Chandra (@rohanchandra30),  Vrushabh Zinage (@Vrushab50081009), Efstathios Bakolas, Joydeep Biswas (@Joydeepb_robots), and Peter Stone (@PeterStone_TX)!

[Rohan Chandra @rohanchandra30]

🚨We present🤖SocialGym 2.0, a simulator for Multi-Agent Social Robot Navigation in Shared Human Spaces !

👨‍💻Code:
https://t.co/yN7shmDhG3
📎Preprint:
https://t.co/12meyhixBl
📄 Docs: https://t.co/IndPaBUMIc

🧵

[Rohan Chandra @rohanchandra30]

What's holding back service & home robotics is the last mile challenge. How can robots navigate in constrained spaces densely packed with human safely & efficiently?

We built a robot🤖that can do this safely, smoothly, & without deadlocks.

Here's how🧵

[Rohan Chandra @rohanchandra30]

✨Excited to announce our paper,

🤖iPLAN🤖: Intent-Aware Planning in Heterogeneous Traffic via Distributed Multi-Agent Reinforcement Learning,

has been accepted for an Oral presentation at #CoRL2023 @corl_conf!

🧵(1/6)
#AutonomousVehicles🚗

[Joydeep Biswas @Joydeepb_robots]

We are thrilled to release CodeBotler and RoboEval to deploy and evaluate LLMs for programming service mobile robots.
https://t.co/f74WCHtVev

Joint work with a fantastic team from @amrl_ut + @arjunguha's group at NU.

A short 🧵, 1/8

[Multi-Robot and Multi-Agent Systems Symposium 2023 @MultiRobotSys]

#multirobotsystems #multiagentsystems #planning #deeplearning #AI #robotics

@lorenzo_s83 , @cjdamato, @NoraRobots, Alyssa Pierson, @ieee_ras_mrs

[Multi-Robot and Multi-Agent Systems Symposium 2023 @MultiRobotSys]

The International Symposium on Multi-Robot & Multi-Agent System will be held on December 4 -5, 2023, in-person at Boston University in Boston, MA

Website: https://t.co/yGvaWDKXhH
CfP: https://t.co/l9QiGI0Uof

Paper Submission Deadline: June, 26, 2023

[Joydeep Biswas @Joydeepb_robots]

The 12th Autonomous F1/10 Grand Prix will be held at CPS-IoT Week, San Antonio, TX, May 8-9. Come cheer on the autonomous racers!

Co-Organizers: @Joydeepb_robots, @XuesuXiao, Rahul Mangharam
Student Organizers: @rmeno12 , Arnav Iyer, Shakeel Samsudeen, Pranav Atreya
@f1tenth

[RSS Pioneers @RSSPioneers]

Happy #TBT! This week's #RSSPioneers throwback features Rohan Chandra (@rohanchandra30), a 2022 RSS Pioneer.

He is a postdoctoral research fellow working at @UTAustin and a graduate of @umdcs.

Find out more about him in our 🧵👇!

[Rohan Chandra @rohanchandra30]

Now accepting contributions to our RSS 2023 Workshop on Multi-Agent Planning and Navigation in Challenging Environments on July 10 in Korea

Submission: https://t.co/g90NEtlvN0

Deadline: May 25, 2023

@RoboticsSciSys @PeterStone_TX @Joydeepb_robots @negar_mehr @utlarg @amrl_ut

[Peter Stone @PeterStone_TX]

A super exciting accomplishment by my Sony AI team. Surely one of the most widespread commercial deployments of reinforcement learning!