no code implementations • 29 Mar 2024 • Zhengmao He, Kun Lei, Yanjie Ze, Koushil Sreenath, Zhongyu Li, Huazhe Xu
Our approach is validated through simulations and real-world experiments, demonstrating the robot's ability to perform tasks that demand mobility and high precision, such as lifting a basket from the ground while moving, closing a dishwasher, pressing a button, and pushing a door.
no code implementations • 29 Feb 2024 • Ilija Radosavovic, Bike Zhang, Baifeng Shi, Jathushan Rajasegaran, Sarthak Kamat, Trevor Darrell, Koushil Sreenath, Jitendra Malik
We cast real-world humanoid control as a next token prediction problem, akin to predicting the next word in language.
1 code implementation • 7 Feb 2024 • Will Lavanakul, Jason J. Choi, Koushil Sreenath, Claire J. Tomlin
As such, we believe that the new notion of the discriminating hyperplane offers a more generalizable direction towards designing safety filters, encompassing and extending existing certificate-function-based or safe RL methodologies.
no code implementations • 30 Jan 2024 • Zhongyu Li, Xue Bin Peng, Pieter Abbeel, Sergey Levine, Glen Berseth, Koushil Sreenath
Going beyond focusing on a single locomotion skill, we develop a general control solution that can be used for a range of dynamic bipedal skills, from periodic walking and running to aperiodic jumping and standing.
no code implementations • 26 Oct 2023 • Jason J. Choi, Donggun Lee, Boyang Li, Jonathan P. How, Koushil Sreenath, Sylvia L. Herbert, Claire J. Tomlin
We also formulate a zero-sum differential game between the control and disturbance, where the inevitable FRT is characterized by the zero-superlevel set of the value function.
1 code implementation • 18 Sep 2023 • Yen-Jen Wang, Bike Zhang, Jianyu Chen, Koushil Sreenath
Large language models (LLMs) pre-trained on vast internet-scale data have showcased remarkable capabilities across diverse domains.
no code implementations • 6 Mar 2023 • Ilija Radosavovic, Tete Xiao, Bike Zhang, Trevor Darrell, Jitendra Malik, Koushil Sreenath
Humanoid robots that can autonomously operate in diverse environments have the potential to help address labour shortages in factories, assist elderly at homes, and colonize new planets.
1 code implementation • 28 Feb 2023 • Yifan Zeng, Suiyi He, Han Hoang Nguyen, Yihan Li, Zhongyu Li, Koushil Sreenath, Jun Zeng
This work introduces a novel control strategy called Iterative Linear Quadratic Regulator for Iterative Tasks (i2LQR), which aims to improve closed-loop performance with local trajectory optimization for iterative tasks in a dynamic environment.
no code implementations • 19 Feb 2023 • Zhongyu Li, Xue Bin Peng, Pieter Abbeel, Sergey Levine, Glen Berseth, Koushil Sreenath
This work aims to push the limits of agility for bipedal robots by enabling a torque-controlled bipedal robot to perform robust and versatile dynamic jumps in the real world.
no code implementations • 27 Jan 2023 • Fernando Castañeda, Haruki Nishimura, Rowan Mcallister, Koushil Sreenath, Adrien Gaidon
Learning-based control approaches have shown great promise in performing complex tasks directly from high-dimensional perception data for real robotic systems.
no code implementations • 10 Oct 2022 • Xiaoyu Huang, Zhongyu Li, Yanzhen Xiang, Yiming Ni, Yufeng Chi, Yunhao Li, Lizhi Yang, Xue Bin Peng, Koushil Sreenath
We present a reinforcement learning (RL) framework that enables quadrupedal robots to perform soccer goalkeeping tasks in the real world.
1 code implementation • 12 Sep 2022 • Gilbert Feng, Hongbo Zhang, Zhongyu Li, Xue Bin Peng, Bhuvan Basireddy, Linzhu Yue, Zhitao Song, Lizhi Yang, Yunhui Liu, Koushil Sreenath, Sergey Levine
In this work, we introduce a framework for training generalized locomotion (GenLoco) controllers for quadrupedal robots.
no code implementations • 23 Aug 2022 • Fernando Castañeda, Jason J. Choi, Wonsuhk Jung, Bike Zhang, Claire J. Tomlin, Koushil Sreenath
This feasibility analysis results in a set of richness conditions that the available information about the system should satisfy to guarantee that a safe control action can be found at all times.
no code implementations • 1 Aug 2022 • Yandong Ji, Zhongyu Li, Yinan Sun, Xue Bin Peng, Sergey Levine, Glen Berseth, Koushil Sreenath
Developing algorithms to enable a legged robot to shoot a soccer ball to a given target is a challenging problem that combines robot motion control and planning into one task.
no code implementations • 29 Jun 2022 • Chenyu Yang, Guo Ning Sue, Zhongyu Li, Lizhi Yang, Haotian Shen, Yufeng Chi, Akshara Rai, Jun Zeng, Koushil Sreenath
We develop and demonstrate one of the first collaborative autonomy framework that is able to move a cable-towed load, which is too heavy to move by a single robot, through narrow spaces with real-time feedback and reactive planning in experiments.
no code implementations • 30 May 2022 • Ashish Kumar, Zhongyu Li, Jun Zeng, Deepak Pathak, Koushil Sreenath, Jitendra Malik
In this work, we leverage recent advances in rapid adaptation for locomotion control, and extend them to work on bipedal robots.
no code implementations • 11 May 2022 • Zhongyu Li, Jun Zeng, Akshay Thirugnanam, Koushil Sreenath
Furthermore, we illustrate that the found linear model is able to provide guarantees by safety-critical optimal control framework, e. g., Model Predictive Control with Control Barrier Functions, on an example of autonomous navigation using Cassie while taking advantage of the agility provided by the RL-based controller.
no code implementations • 15 Mar 2022 • Karan P. Jain, Prasanth Kotaru, Massimiliano de Sa, Koushil Sreenath, Mark W. Mueller
Finally, we present experiments demonstrating the use of a two-quadcopter tethered system as compared to a one-quadcopter tethered system in a cluttered environment, such as passing through a window and grasping an object over an obstacle.
no code implementations • 10 Mar 2022 • Shuxiao Chen, Bike Zhang, Mark W. Mueller, Akshara Rai, Koushil Sreenath
Reinforcement learning (RL) has become a promising approach to developing controllers for quadrupedal robots.
no code implementations • 4 Mar 2022 • Lizhi Yang, Zhongyu Li, Jun Zeng, Koushil Sreenath
We leverage BO to learn the control parameters used in the HZD-based controller.
no code implementations • 4 Mar 2022 • Arjun Sripathy, Andreea Bobu, Zhongyu Li, Koushil Sreenath, Daniel S. Brown, Anca D. Dragan
As a result 1) all user feedback can contribute to learning about every emotion; 2) the robot can generate trajectories for any emotion in the space instead of only a few predefined ones; and 3) the robot can respond emotively to user-generated natural language by mapping it to a target VAD.
no code implementations • 4 Jan 2022 • Hengbo Ma, Bike Zhang, Masayoshi Tomizuka, Koushil Sreenath
By embedding the optimization procedure of the exponential control barrier function based quadratic program (ECBF-QP) as a differentiable layer within a deep learning architecture, we propose a differentiable safety-critical control framework that enables generalization to new environments for high relative-degree systems with forward invariance guarantees.
no code implementations • 13 Sep 2021 • Zhongyu Li, Jun Zeng, Shuxiao Chen, Koushil Sreenath
This demonstrates reliable autonomy to drive the robot to safely avoid obstacles while walking to the goal location in various kinds of height-constrained cluttered environments.
no code implementations • 7 Aug 2021 • Shuxiao Chen, Xiangyu Wu, Mark W. Mueller, Koushil Sreenath
The capabilities of autonomous flight with unmanned aerial vehicles (UAVs) have significantly increased in recent times.
no code implementations • 18 Jul 2021 • Akshay Thirugnanam, Jun Zeng, Koushil Sreenath
A dual optimization problem is introduced to represent the minimum distance between polytopes and the Lagrangian function for the dual form is applied to construct a control barrier function.
no code implementations • 1 Jul 2021 • Scott Gilroy, Derek Lau, Lizhi Yang, Ed Izaguirre, Kristen Biermayer, Anxing Xiao, Mengti Sun, Ayush Agrawal, Jun Zeng, Zhongyu Li, Koushil Sreenath
The resulted jumping mode is utilized in an autonomous navigation pipeline that leverages a search-based global planner and a local planner to enable the robot to reach the goal location by walking.
no code implementations • 13 Jun 2021 • Fernando Castañeda, Jason J. Choi, Bike Zhang, Claire J. Tomlin, Koushil Sreenath
However, since these constraints rely on a model of the system, when this model is inaccurate the guarantees of safety and stability can be easily lost.
2 code implementations • 21 May 2021 • Jun Zeng, Zhongyu Li, Koushil Sreenath
In the existing approaches, the feasibility of the optimization and the system safety cannot be enhanced at the same time theoretically.
no code implementations • 6 Apr 2021 • Jason J. Choi, Donggun Lee, Koushil Sreenath, Claire J. Tomlin, Sylvia L. Herbert
This paper works towards unifying two popular approaches in the safety control community: Hamilton-Jacobi (HJ) reachability and Control Barrier Functions (CBFs).
no code implementations • 26 Mar 2021 • Zhongyu Li, Xuxin Cheng, Xue Bin Peng, Pieter Abbeel, Sergey Levine, Glen Berseth, Koushil Sreenath
Developing robust walking controllers for bipedal robots is a challenging endeavor.
1 code implementation • 23 Mar 2021 • Suiyi He, Jun Zeng, Bike Zhang, Koushil Sreenath
This paper develops a new control design for guaranteeing a vehicle's safety during lane change maneuvers in a complex traffic environment.
no code implementations • 15 Jan 2021 • Sylvia Herbert, Jason J. Choi, Suvansh Sanjeev, Marsalis Gibson, Koushil Sreenath, Claire J. Tomlin
However, work to learn and update safety analysis is limited to small systems of about two dimensions due to the computational complexity of the analysis.
no code implementations • 14 Nov 2020 • Fernando Castañeda, Jason J. Choi, Bike Zhang, Claire J. Tomlin, Koushil Sreenath
This paper presents a method to design a min-norm Control Lyapunov Function (CLF)-based stabilizing controller for a control-affine system with uncertain dynamics using Gaussian Process (GP) regression.
2 code implementations • 22 Jul 2020 • Jun Zeng, Bike Zhang, Koushil Sreenath
In order to obtain safe optimal performance in the context of set invariance, we present a safety-critical model predictive control strategy utilizing discrete-time control barrier functions (CBFs), which guarantees system safety and accomplishes optimal performance via model predictive control.
no code implementations • 14 May 2020 • Quan Nguyen, Koushil Sreenath
We present a novel method of optimal robust control through quadratic programs that offers tracking stability while subject to input and state-based constraints as well as safety-critical constraints for nonlinear dynamical robotic systems in the presence of model uncertainty.
no code implementations • 16 Apr 2020 • Jason Choi, Fernando Castañeda, Claire J. Tomlin, Koushil Sreenath
In this paper, the issue of model uncertainty in safety-critical control is addressed with a data-driven approach.
no code implementations • L4DC 2020 • Fernando Castañeda, Mathias Wulfman, Ayush Agrawal, Tyler Westenbroek, Claire J. Tomlin, S. Shankar Sastry, Koushil Sreenath
The main drawbacks of input-output linearizing controllers are the need for precise dynamics models and not being able to account for input constraints.