no code implementations • ACL 2022 • Qiang Ning, Ben Zhou, Hao Wu, Haoruo Peng, Chuchu Fan, Matt Gardner
News events are often associated with quantities (e. g., the number of COVID-19 patients or the number of arrests in a protest), and it is often important to extract their type, time, and location from unstructured text in order to analyze these quantity events.
1 code implementation • 5 Feb 2025 • Songyuan Zhang, Oswin So, Mitchell Black, Chuchu Fan
However, it is difficult to design distributed CBF-based policies for MAS that can tackle unknown discrete-time dynamics, partial observability, changing neighborhoods, and input constraints, especially when a distributed high-performance nominal policy that can achieve the task is unavailable.
1 code implementation • 4 Feb 2025 • Yongchao Chen, Yilun Hao, Yueying Liu, Yang Zhang, Chuchu Fan
Existing methods fail to effectively steer Large Language Models (LLMs) between textual reasoning and code generation, leaving symbolic computing capabilities underutilized.
no code implementations • 29 Oct 2024 • Oswin So, Cheng Ge, Chuchu Fan
Current reinforcement-learning methods are unable to directly learn policies that solve the minimum cost reach-avoid problem to minimize cumulative costs subject to the constraints of reaching the goal and avoiding unsafe states, as the structure of this new optimization problem is incompatible with current methods.
no code implementations • 15 Oct 2024 • Yilun Hao, Yang Zhang, Chuchu Fan
We apply LLMFP to 9 planning problems, ranging from multi-constraint decision making to multi-step planning problems, and demonstrate that LLMFP achieves on average 83. 7% and 86. 8% optimal rate across 9 tasks for GPT-4o and Claude 3. 5 Sonnet, significantly outperforming the best baseline (direct planning with OpenAI o1-preview) with 37. 6% and 40. 7% improvements.
1 code implementation • 4 Oct 2024 • Yongchao Chen, Harsh Jhamtani, Srinagesh Sharma, Chuchu Fan, Chi Wang
Textual reasoning has inherent limitations in solving tasks with challenges in math, logics, optimization, and searching, which is unlikely to be solved by simply scaling up the model and data size.
no code implementations • 20 Aug 2024 • Ruixiao Yang, Chuchu Fan
We introduce the multi-agent flying sidekick traveling salesman problem (MA-FSTSP) on road networks, extending the single truck-drone model to multiple trucks, each carrying multiple drones while considering full road networks for truck restrictions and flexible drone routes.
no code implementations • 28 May 2024 • Feiyang Cai, Chuchu Fan, Stanley Bak
We demonstrate the effectiveness of our approach in terms of both accuracy and scalability using two case studies: an autonomous aircraft taxiing system and an advanced emergency braking system.
no code implementations • 18 Apr 2024 • Yilun Hao, Yongchao Chen, Yang Zhang, Chuchu Fan
We start with TravelPlanner as the primary use case and show that our framework achieves a success rate of 93. 9% and is effective with diverse paraphrased prompts.
no code implementations • 9 Apr 2024 • Kunal Garg, Songyuan Zhang, Jacob Arkin, Chuchu Fan
We compare their performance with a graph-based planner in terms of effectiveness in helping the MRS reach their target locations and computational time.
no code implementations • 1 Apr 2024 • Mingxin Yu, Chenning Yu, M-Mahdi Naddaf-Sh, Devesh Upadhyay, Sicun Gao, Chuchu Fan
Our method combines the strength of CBF for real-time collision-avoidance control and RRT for long-horizon motion planning, by using CBF-induced neural controller (CBF-INC) to generate control signals that steer the system towards sampled configurations by RRT.
no code implementations • 14 Feb 2024 • Allen M. Wang, Oswin So, Charles Dawson, Darren T. Garnier, Cristina Rea, Chuchu Fan
The policy training environment is a hybrid physics and machine learning model trained on simulations of the SPARC primary reference discharge (PRD) ramp-down, an upcoming burning plasma scenario which we use as a testbed.
1 code implementation • 13 Feb 2024 • Yongchao Chen, Jacob Arkin, Yilun Hao, Yang Zhang, Nicholas Roy, Chuchu Fan
Prompt optimization aims to find the best prompt to a large language model (LLM) for a given task.
1 code implementation • 21 Nov 2023 • Songyuan Zhang, Kunal Garg, Chuchu Fan
We consider the problem of designing distributed collision-avoidance multi-agent control in large-scale environments with potentially moving obstacles, where a large number of agents are required to maintain safety using only local information and reach their goals.
no code implementations • 10 Oct 2023 • Charles Dawson, Chuchu Fan
We show that adversarial optimization is liable to severely overestimate the robustness of the optimized dispatch (when the adversary encounters a local minimum), leading the operator to falsely believe that their dispatch is secure.
no code implementations • 10 Sep 2023 • Yue Meng, Chuchu Fan
We conduct experiments on six tasks, where our method with the backup policy outperforms the classical methods (MPC, STL-solver), model-free and model-based RL methods in STL satisfaction rate, especially on tasks with complex STL specifications while being 10X-100X faster than the classical methods.
1 code implementation • 14 Jun 2023 • Songyuan Zhang, Chuchu Fan
The Lyapunov theory offers a solution for stabilizing control systems, still, current methods relying on Lyapunov functions require access to complete dynamics or samples of system executions throughout the entire state space.
3 code implementations • 10 Jun 2023 • Yongchao Chen, Jacob Arkin, Charles Dawson, Yang Zhang, Nicholas Roy, Chuchu Fan
Rather than using LLMs to directly plan task sub-goals, we instead perform few-shot translation from natural language task descriptions to an intermediate task representation that can then be consumed by a TAMP algorithm to jointly solve the task and motion plan.
3 code implementations • 12 May 2023 • Yongchao Chen, Rujul Gandhi, Yang Zhang, Chuchu Fan
Then, we finetune T5 models on the lifted versions (i. e., the specific Atomic Propositions (AP) are hidden) of the NL and TL.
1 code implementation • 25 Mar 2023 • Songyuan Zhang, Yumeng Xiu, Guannan Qu, Chuchu Fan
Specifically, we treat a large networked dynamical system as an interconnection of smaller subsystems and develop methods that can find each subsystem a decentralized controller and an ISS Lyapunov function; the latter can be collectively composed to prove the global stability of the system.
no code implementations • 18 Mar 2023 • Yue Meng, Chuchu Fan
For each system mode, we first learn an NN Lyapunov function and an NN controller to ensure the states within the region of attraction (RoA) can be stabilized.
no code implementations • 7 Mar 2023 • Yue Meng, Sai Vemprala, Rogerio Bonatti, Chuchu Fan, Ashish Kapoor
In this work, we propose Control Barrier Transformer (ConBaT), an approach that learns safe behaviors from demonstrations in a self-supervised fashion.
no code implementations • 16 Oct 2022 • Ruipeng Zhang, Chenning Yu, Jingkai Chen, Chuchu Fan, Sicun Gao
Learning-based methods have shown promising performance for accelerating motion planning, but mostly in the setting of static environments.
no code implementations • 16 Sep 2022 • Yue Meng, Zeng Qiu, Md Tawhid Bin Waez, Chuchu Fan
Recent work provides a data-driven approach to compute the density distribution of autonomous systems' forward reachable states online.
no code implementations • 4 Mar 2022 • Jingkai Chen, Jiaoyang Li, Yijiang Huang, Caelan Garrett, Dawei Sun, Chuchu Fan, Andreas Hofmann, Caitlin Mueller, Sven Koenig, Brian C. Williams
Multi-robot assembly systems are becoming increasingly appealing in manufacturing due to their ability to automatically, flexibly, and quickly construct desired structural designs.
1 code implementation • 6 Jan 2022 • Zengyi Qin, Dawei Sun, Chuchu Fan
Control certificates based on barrier functions have been a powerful tool to generate probably safe control policies for dynamical systems.
no code implementations • 2 Oct 2021 • Hiroyasu Tsukamoto, Soon-Jo Chung, Jean-Jacques Slotine, Chuchu Fan
This paper presents a theoretical overview of a Neural Contraction Metric (NCM): a neural network model of an optimal contraction metric and corresponding differential Lyapunov function, the existence of which is a necessary and sufficient condition for incremental exponential stability of non-autonomous nonlinear system trajectories.
no code implementations • 14 Sep 2021 • Yue Meng, Dawei Sun, Zeng Qiu, Md Tawhid Bin Waez, Chuchu Fan
State density distribution, in contrast to worst-case reachability, can be leveraged for safety-related problems to better quantify the likelihood of the risk for potentially hazardous situations.
no code implementations • 14 Sep 2021 • Charles Dawson, Zengyi Qin, Sicun Gao, Chuchu Fan
Safety and stability are common requirements for robotic control systems; however, designing safe, stable controllers remains difficult for nonlinear and uncertain models.
1 code implementation • 14 Sep 2021 • Yue Meng, Zengyi Qin, Chuchu Fan
Reactive and safe agent modelings are important for nowadays traffic simulator designs and safe planning applications.
no code implementations • 24 Jun 2021 • Zengyi Qin, Yuxiao Chen, Chuchu Fan
We study constrained reinforcement learning (CRL) from a novel perspective by setting constraints directly on state density functions, rather than the value functions considered by previous works.
no code implementations • 16 Feb 2021 • Jingkai Chen, Brian Williams, Chuchu Fan
Planning in hybrid systems with both discrete and continuous control variables is important for dealing with real-world applications such as extra-planetary exploration and multi-vehicle transportation systems.
Continuous Control
Robotics
Systems and Control
Systems and Control
1 code implementation • ICLR 2021 • Zengyi Qin, Kaiqing Zhang, Yuxiao Chen, Jingkai Chen, Chuchu Fan
We propose a novel joint-learning framework that can be implemented in a decentralized fashion, with generalization guarantees for certain function classes.
no code implementations • 16 Dec 2020 • Jingkai Chen, Jiaoyang Li, Chuchu Fan, Brian Williams
We present a scalable and effective multi-agent safe motion planner that enables a group of agents to move to their desired locations while avoiding collisions with obstacles and other agents, with the presence of rich obstacles, high-dimensional, nonlinear, nonholonomic dynamics, actuation limits, and disturbances.
Motion Planning
Robotics
Multiagent Systems
no code implementations • 6 Nov 2020 • Yuxiao Chen, Ugo Rosolia, Chuchu Fan, Aaron D. Ames, Richard Murray
Motion planning in environments with multiple agents is critical to many important autonomous applications such as autonomous vehicles and assistive robots.
no code implementations • 1 Apr 2020 • Chuchu Fan, Xin Qin, Yuan Xia, Aditya Zutshi, Jyotirmoy Deshmukh
Our technique uses model simulations to learn {\em surrogate models}, and uses {\em conformal inference} to provide probabilistic guarantees on the satisfaction of a given STL property.
no code implementations • NAACL 2019 • Qiang Ning, Hangfeng He, Chuchu Fan, Dan Roth
For many structured learning tasks, the data annotation process is complex and costly.
no code implementations • SEMEVAL 2018 • Qiang Ning, Zhongzhi Yu, Chuchu Fan, Dan Roth
As a result, only a small number of documents are typically annotated, limiting the coverage of various lexical/semantic phenomena.
no code implementations • 18 Apr 2018 • Qiang Ning, Zhongzhi Yu, Chuchu Fan, Dan Roth
As a result, only a small number of documents are typically annotated, limiting the coverage of various lexical/semantic phenomena.