Search Results for author: Changliu Liu

Found 37 papers, 21 papers with code

An Optimal Control Framework for Influencing Human Driving Behavior in Mixed-Autonomy Traffic

no code implementations23 Sep 2023 Anirudh Chari, Rui Chen, Jaskaran Grover, Changliu Liu

Given these results, the main contribution of our framework is its versatility in a wide spectrum of influence objectives and mixed-autonomy configurations.

Autonomous Vehicles

Safety Index Synthesis with State-dependent Control Space

no code implementations21 Sep 2023 Rui Chen, WeiYe Zhao, Changliu Liu

This paper introduces an approach for synthesizing feasible safety indices to derive safe control laws under state-dependent control spaces.

Robotic Planning under Hierarchical Temporal Logic Specifications

no code implementations20 Aug 2023 Xusheng Luo, Shaojun Xu, Ruixuan Liu, Changliu Liu

In order to maximize the potential of LTL specifications, we capitalized on the intrinsic structure of tasks and introduced a hierarchical structure to LTL specifications.

State-wise Constrained Policy Optimization

1 code implementation21 Jun 2023 WeiYe Zhao, Rui Chen, Yifan Sun, Tianhao Wei, Changliu Liu

In particular, we introduce the framework of Maximum Markov Decision Process, and prove that the worst-case safety violation is bounded under SCPO.

Autonomous Driving reinforcement-learning +2

GUARD: A Safe Reinforcement Learning Benchmark

1 code implementation23 May 2023 WeiYe Zhao, Rui Chen, Yifan Sun, Ruixuan Liu, Tianhao Wei, Changliu Liu

Due to the diversity of algorithms and tasks, it remains difficult to compare existing safe RL algorithms.

Autonomous Driving reinforcement-learning +2

Safe and Sample-efficient Reinforcement Learning for Clustered Dynamic Environments

1 code implementation24 Mar 2023 Hongyi Chen, Changliu Liu

This study proposes a safe and sample-efficient reinforcement learning (RL) framework to address two major challenges in developing applicable RL algorithms: satisfying safety constraints and efficiently learning with limited samples.

reinforcement-learning Reinforcement Learning (RL) +1

State-wise Safe Reinforcement Learning: A Survey

no code implementations6 Feb 2023 WeiYe Zhao, Tairan He, Rui Chen, Tianhao Wei, Changliu Liu

Despite the tremendous success of Reinforcement Learning (RL) algorithms in simulation environments, applying RL to real-world applications still faces many challenges.

Autonomous Driving reinforcement-learning +3

AutoCost: Evolving Intrinsic Cost for Zero-violation Reinforcement Learning

no code implementations24 Jan 2023 Tairan He, WeiYe Zhao, Changliu Liu

Results show that the converged policies with intrinsic costs in all environments achieve zero constraint violation and comparable performance with baselines.

reinforcement-learning Reinforcement Learning (RL)

First Three Years of the International Verification of Neural Networks Competition (VNN-COMP)

no code implementations14 Jan 2023 Christopher Brix, Mark Niklas Müller, Stanley Bak, Taylor T. Johnson, Changliu Liu

This paper presents a summary and meta-analysis of the first three iterations of the annual International Verification of Neural Networks Competition (VNN-COMP) held in 2020, 2021, and 2022.

Image Classification reinforcement-learning +1

The Third International Verification of Neural Networks Competition (VNN-COMP 2022): Summary and Results

2 code implementations20 Dec 2022 Mark Niklas Müller, Christopher Brix, Stanley Bak, Changliu Liu, Taylor T. Johnson

This report summarizes the 3rd International Verification of Neural Networks Competition (VNN-COMP 2022), held as a part of the 5th Workshop on Formal Methods for ML-Enabled Autonomous Systems (FoMLAS), which was collocated with the 34th International Conference on Computer-Aided Verification (CAV).

Safe Control Under Input Limits with Neural Control Barrier Functions

1 code implementation20 Nov 2022 Simin Liu, Changliu Liu, John Dolan

We propose new methods to synthesize control barrier function (CBF)-based safe controllers that avoid input saturation, which can cause safety violations.

BioSLAM: A Bio-inspired Lifelong Memory System for General Place Recognition

no code implementations30 Aug 2022 Peng Yin, Abulikemu Abuduweili, Shiqi Zhao, Changliu Liu, Sebastian Scherer

We present BioSLAM, a lifelong SLAM framework for learning various new appearances incrementally and maintaining accurate place recognition for previously visited areas.

ARC -- Actor Residual Critic for Adversarial Imitation Learning

no code implementations5 Jun 2022 Ankur Deka, Changliu Liu, Katia Sycara

In AIL, an artificial adversary's misclassification is used as a reward signal that is optimized by any standard Reinforcement Learning (RL) algorithm.

Continuous Control Imitation Learning +1

Learning from Physical Human Feedback: An Object-Centric One-Shot Adaptation Method

1 code implementation9 Mar 2022 Alvin Shek, Bo Ying Su, Rui Chen, Changliu Liu

For robots to be effectively deployed in novel environments and tasks, they must be able to understand the feedback expressed by humans during intervention.

Transferable and Adaptable Driving Behavior Prediction

no code implementations10 Feb 2022 Letian Wang, Yeping Hu, Liting Sun, Wei Zhan, Masayoshi Tomizuka, Changliu Liu

By mimicking humans' cognition model and semantic understanding during driving, we propose HATN, a hierarchical framework to generate high-quality, transferable, and adaptable predictions for driving behaviors in multi-agent dense-traffic environments.

Autonomous Vehicles Trajectory Prediction

Online Adaptation of Neural Network Models by Modified Extended Kalman Filter for Customizable and Transferable Driving Behavior Prediction

no code implementations9 Dec 2021 Letian Wang, Yeping Hu, Changliu Liu

With the feedback of the observed trajectory, the algorithm is applied to neural-network-based models to improve the performance of driving behavior predictions across different human subjects and scenarios.

Autonomous Vehicles

Learn Zero-Constraint-Violation Policy in Model-Free Constrained Reinforcement Learning

1 code implementation25 Nov 2021 Haitong Ma, Changliu Liu, Shengbo Eben Li, Sifa Zheng, Wenchao Sun, Jianyu Chen

Existing methods mostly use the posterior penalty for dangerous actions, which means that the agent is not penalized until experiencing danger.

reinforcement-learning Reinforcement Learning (RL)

Joint Synthesis of Safety Certificate and Safe Control Policy using Constrained Reinforcement Learning

1 code implementation15 Nov 2021 Haitong Ma, Changliu Liu, Shengbo Eben Li, Sifa Zheng, Jianyu Chen

This paper proposes a novel approach that simultaneously synthesizes the energy-function-based safety certificate and learns the safe control policy with CRL.

reinforcement-learning Reinforcement Learning (RL)

Safe Control with Neural Network Dynamic Models

1 code implementation3 Oct 2021 Tianhao Wei, Changliu Liu

It has been extensively studied regarding how to derive a safe control law with a control-affine analytical dynamic model.

The Second International Verification of Neural Networks Competition (VNN-COMP 2021): Summary and Results

3 code implementations31 Aug 2021 Stanley Bak, Changliu Liu, Taylor Johnson

This report summarizes the second International Verification of Neural Networks Competition (VNN-COMP 2021), held as a part of the 4th Workshop on Formal Methods for ML-Enabled Autonomous Systems that was collocated with the 33rd International Conference on Computer-Aided Verification (CAV).

Data Efficient Human Intention Prediction: Leveraging Neural Network Verification and Expert Guidance

no code implementations16 Aug 2021 Ruixuan Liu, Changliu Liu

Predicting human intention is critical to facilitating safe and efficient human-robot collaboration (HRC).

Data Augmentation

Online Verification of Deep Neural Networks under Domain Shift or Network Updates

no code implementations24 Jun 2021 Tianhao Wei, Changliu Liu

Although neural networks are widely used, it remains challenging to formally verify the safety and robustness of neural networks in real-world applications.

Management

Provably Safe Tolerance Estimation for Robot Arms via Sum-of-Squares Programming

1 code implementation18 Apr 2021 WeiYe Zhao, Suqin He, Changliu Liu

Tolerance estimation problems are prevailing in engineering applications.

Flexible MPC-based Conflict Resolution Using Online Adaptive ADMM

no code implementations25 Mar 2021 Jerry An, Giulia Giordano, Changliu Liu

We propose a decentralized conflict resolution method for autonomous vehicles based on a novel extension to the Alternating Directions Method of Multipliers (ADMM), called Online Adaptive ADMM (OA-ADMM), and on Model Predictive Control (MPC).

Autonomous Vehicles Motion Planning

Augmenting GAIL with BC for sample efficient imitation learning

2 code implementations21 Jan 2020 Rohit Jena, Changliu Liu, Katia Sycara

Behavior cloning and GAIL are two widely used methods for performing imitation learning.

Imitation Learning

Robust Online Model Adaptation by Extended Kalman Filter with Exponential Moving Average and Dynamic Multi-Epoch Strategy

1 code implementation L4DC 2020 Abulikemu Abuduweili, Changliu Liu

The challenge motivates the adoption of online adaptation algorithms to update prediction models in real-time to improve the prediction performance.

Adaptable Human Intention and Trajectory Prediction for Human-Robot Collaboration

1 code implementation11 Sep 2019 Abulikemu Abuduweili, Siyan Li, Changliu Liu

The effectiveness and flexibility of the proposed method has been validated in experiments.

Robotics

Safe Control Algorithms Using Energy Functions: A Unified Framework, Benchmark, and New Directions

1 code implementation5 Aug 2019 Tianhao Wei, Changliu Liu

In different methods, the energy function is called a potential function, a safety index, or a barrier function.

Algorithms for Verifying Deep Neural Networks

2 code implementations15 Mar 2019 Changliu Liu, Tomer Arnon, Christopher Lazarus, Clark Barrett, Mykel J. Kochenderfer

Deep neural networks are widely used for nonlinear function approximation with applications ranging from computer vision to control.

Robot Safe Interaction System for Intelligent Industrial Co-Robots

1 code implementation12 Aug 2018 Changliu Liu, Masayoshi Tomizuka

Human-robot interactions have been recognized to be a key element of future industrial collaborative robots (co-robots).

Robotics Systems and Control

The Convex Feasible Set Algorithm for Real Time Optimization in Motion Planning

1 code implementation2 Sep 2017 Changliu Liu, Chung-Yen Lin, Masayoshi Tomizuka

The idea is to find a convex feasible set for the original problem and iteratively solve a sequence of subproblems using the convex constraints.

Optimization and Control Robotics

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