Search Results for author: Koushil Sreenath

Found 36 papers, 7 papers with code

Humanoid Locomotion as Next Token Prediction

no code implementations29 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.

Humanoid Control

Safety Filters for Black-Box Dynamical Systems by Learning Discriminating Hyperplanes

1 code implementation7 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.

Reinforcement Learning (RL)

Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control

no code implementations30 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.

reinforcement-learning Reinforcement Learning (RL)

A Forward Reachability Perspective on Robust Control Invariance and Discount Factors in Reachability Analysis

no code implementations26 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.

Prompt a Robot to Walk with Large Language Models

1 code implementation18 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.

Real-World Humanoid Locomotion with Reinforcement Learning

no code implementations6 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.

reinforcement-learning

i2LQR: Iterative LQR for Iterative Tasks in Dynamic Environments

1 code implementation28 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.

Robust and Versatile Bipedal Jumping Control through Reinforcement Learning

no code implementations19 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.

reinforcement-learning Reinforcement Learning (RL)

In-Distribution Barrier Functions: Self-Supervised Policy Filters that Avoid Out-of-Distribution States

no code implementations27 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.

GenLoco: Generalized Locomotion Controllers for Quadrupedal Robots

1 code implementation12 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.

Recursively Feasible Probabilistic Safe Online Learning with Control Barrier Functions

no code implementations23 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.

Out-of-Distribution Detection

Hierarchical Reinforcement Learning for Precise Soccer Shooting Skills using a Quadrupedal Robot

no code implementations1 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.

Friction Hierarchical Reinforcement Learning +3

Collaborative Navigation and Manipulation of a Cable-towed Load by Multiple Quadrupedal Robots

no code implementations29 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.

Adapting Rapid Motor Adaptation for Bipedal Robots

no code implementations30 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.

Bridging Model-based Safety and Model-free Reinforcement Learning through System Identification of Low Dimensional Linear Models

no code implementations11 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.

Autonomous Navigation Model Predictive Control +2

Tethered Power for a Series of Quadcopters: Analysis and Applications

no code implementations15 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.

Learning Torque Control for Quadrupedal Locomotion

no code implementations10 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.

Position Reinforcement Learning (RL)

Teaching Robots to Span the Space of Functional Expressive Motion

no code implementations4 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.

Learning Differentiable Safety-Critical Control using Control Barrier Functions for Generalization to Novel Environments

no code implementations4 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.

Autonomous Navigation of Underactuated Bipedal Robots in Height-Constrained Environments

no code implementations13 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.

Autonomous Navigation Trajectory Planning

Real-time Geo-localization Using Satellite Imagery and Topography for Unmanned Aerial Vehicles

no code implementations7 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.

Image-Based Localization

Duality-based Convex Optimization for Real-time Obstacle Avoidance between Polytopes with Control Barrier Functions

no code implementations18 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.

Autonomous Navigation for Quadrupedal Robots with Optimized Jumping through Constrained Obstacles

no code implementations1 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.

Autonomous Navigation Decision Making +1

Pointwise Feasibility of Gaussian Process-based Safety-Critical Control under Model Uncertainty

no code implementations13 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.

Enhancing Feasibility and Safety of Nonlinear Model Predictive Control with Discrete-Time Control Barrier Functions

2 code implementations21 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.

Model Predictive Control

Robust Control Barrier-Value Functions for Safety-Critical Control

no code implementations6 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).

valid

Rule-Based Safety-Critical Control Design using Control Barrier Functions with Application to Autonomous Lane Change

1 code implementation23 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.

Scalable Learning of Safety Guarantees for Autonomous Systems using Hamilton-Jacobi Reachability

no code implementations15 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.

Gaussian Process-based Min-norm Stabilizing Controller for Control-Affine Systems with Uncertain Input Effects and Dynamics

no code implementations14 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.

regression

Safety-Critical Model Predictive Control with Discrete-Time Control Barrier Function

2 code implementations22 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.

Car Racing Model Predictive Control

Robust Safety-Critical Control for Dynamic Robotics

no code implementations14 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.