News

Happy Valentine's Day

Happy Thanksgiving!

Congratulations to Changliu for receiving the 2023 ARM Champion Award!

Live demo on robot grinding at ARM Annual Member Meeting

Congratulations Anirudh! Check the video here

Congratulations Weiye!

Congratulations Simin!

Congratulations to Alvin Shek, Bo Ying Su, and Rui Chen for winning the ICRA Outstanding Interaction Paper Award.

Check out the CMU news here.

Congratulations to Jaskaran for his PhD degree, and Yifan for his master degree!

New RA-L paper "Robust and Context-Aware Real-Time Collaborative Robot Handling via Dynamic Gesture Commands"

Congratulations to Dr. Grover, the first PhD from the Intelligent Control Lab!

Check our papers at CoRL 2022.

Congratulations to Ruixuan, Rui, and Jaskaran for the awards at CPHS 2022!

Happy Thanksgiving!

Our recent project enables efficient and safe human-robot collaboration on a co-assembly task. The robot is able to adapt to different environments as well as accomodate various humans behaviors in order to collaborate safely and intelligently.

Check our paper
Jerk-bounded Position Controller with Real-Time Task Modification for Interactive Industrial Robots.

Check our papers at ISFA 2022.

Check our paper at RSS 2022 Workshop.

The U.S. Department of Commerce’s National Institute of Standards and Technology (NIST) awarded AFFOA (Advanced Functional Fabrics of America) and 16 cross-institute collaborators over $11M in funding as part of the American Rescue Act’s Rapid Assistance (for) Coronavirus Economic Response (RACER) program. We are excited to be part of the project to automate mask production using robotics. Read more here.

Check our paper
Learning from Physical Human Feedback - An Object-Centric One-Shot Adaptation Method.

Check out the video for a virtual lab tour here.

Jaskaran passed his PhD thesis proposal for the work on "System Identification and Control of Multiagent Systems Through Interactions".

We demonstrated our work on human-robot collaboration during President Biden's visit at Mill 19.

With the support of the NSF career award, we will continue to work on safety of autonomous systems.

ATI shared the story of our project on robotic weld bead removal project. Read the post here.

Congratulations Tianhao!

Check our paper
* Model-free Safe Control for Zero-Violation Reinforcement Learning.

Check out our workshop on Safe Control and Learning under Uncertainty; and our papers 1) System Identification of Safe Controllers Using Inverse Optimization; 2) Safe Adaptation with Multiplicative Uncertainties Using Robust Safe Set Algorithm

Learn more of our recent work through the mini workshop.

Ruixuan finishes his master study on Data-Efficient Behavior Prediction for Safe Human-Robot Collaboration. His thesis can be found here. His thesis talk can be found here.

Changliu talks about our recent work on Safety-critical learning and control for collaborative robots.

The organizers reported the results of VNN-COMP'21 on 4th Workshop on Formal Methods for ML-Enabled Autonomous Systems (FoMLAS) affiliated with CAV 2021.

Find in our YouTube channel the presentation videos for the following paper.
* Flexible MPC-based Conflict Resolution Using Online Adaptive ADMM.
* Feasible Region-based Identification Using Duality.

Find in our YouTube channel the presentation video for the following paper.
* Distributed Motion Coordination Using Convex Feasible Set Based Model Predictive Control.

Congratulations Jaskaran and Weiye!

Find in our YouTube channel the presentation video for the following paper.
* Human Motion Prediction Using Adaptable Recurrent Neural Networks and Inverse Kinematics (ACC).

Changliu talks about our recent work on Verification and Adaptation of Deep Neural Networks.

Chase Noren, 2nd year PhD student in the lab, gets the prestigious Uber PhD Fellowship.

Find in our YouTube channel the presentation videos for the following papers.
* Tolerance-guided Policy Learning for Adaptable and Transferrable Delicate Industrial Insertion (CoRL, 2020).

Find in our YouTube channel the presentation videos for the following papers.
* Contact-Rich Trajectory Generation in Confined Environment using Iterative Convex Optimization (DSCC).
* Multi-car Convex Feasible Set Algorithm in Trajectory Planning (DSCC).

Weiye's paper Contact-Rich Trajectory Generation in Confined Environments Using Iterative Convex Optimization gets the Best Student Paper Finalist in DSCC 2020.

Find in our YouTube channel the presentation video for the following paper.
* Experimental Evaluation of Human Motion Prediction Toward Safe and Efficient Human Robot Collaboration (ACC).

Find in our YouTube channel the presentation videos for the following papers.
* Robust online model adaptation by EKF with exponential moving average and dynamic multi-epoch strategy (L4DC).
* Why does symmetry cause deadlocks (IFAC World Congress).
* Experimental evaluation of human motion prediction toward safe and efficient human robot collaboration (ACC).

The project "Hierarchical Motion Planning for Efficient and Provably Safe Human-Robot Interactions" received 2019 Amazon Research Reward.

The video here shows the recent progress of the project Automatic Onsite Polishing of Large Complex Surfaces by Real Time Planning and Control supported by the Advanced Robotics for Manufacturing Institute. This project is in collaboration with Siemens and Yaskawa.

Tianhao presented the paper Safe control algorithms using energy functions - A unified framework, benchmark, and new directions in the 58th IEEE Conference on Decision and Control.

Siyan presented the paper Adaptable Human Intention and Trajectory Prediction for Human-Robot Collaboration in the AAAI Fall Symposium Series - AI for HRI.

The book "Designing Robot Behavior in Human-Robot Interactions" is available here.

Jaskaran Grover, 2nd year PhD student in the lab, gets the prestigious Uber Presidential Fellowship.

This tutorial provides detailed instruction on how to use NeuralVerification.jl to verify various neural networks. It is available on YouTube (link).

The Robotiq Blog posted an interview with Changliu (link). In this interview, Changliu talks cobot safety, the importance of having realistic expectations of what cobots can and can't do and her vision of a manufacturing world after cobots.

We will organize a workshop at Stanford on June 7 and June 10 introducing the toolbox NeuralVerification.jl.

We will present our paper "AGen - Adaptable generative prediction networks for autonomous driving" in IV2019.

A group of high school students and teachers from Choate visited the Intelligent Control Lab.

Our paper "NeuralVerification.jl - Algorithms for Verifying Deep Neural Networks" has won the Best Applied Paper award at the ICLR 2019 Workshop on Debugging Machine Learning Models.

FANUC donated an industrial robot arm LR Mate 200iD/7L to the Intelligent Control Lab to support our research.

The webinar is available at this link.

This paper surveys emerging algorithms to verify whether a deep neural network satisfies certain input-output properties.