no code implementations • EMNLP 2021 • Shuqun Li, Liang Yang, Weidong He, Shiqi Zhang, Jingjie Zeng, Hongfei Lin
At the sentence level, we leverage the metaphor information of words that except the target word in the sentence to strengthen the reasoning ability of our model via a novel label-enhanced contextualized representation.
no code implementations • 3 Apr 2024 • Zhigen Zhao, Shuo Cheng, Yan Ding, Ziyi Zhou, Shiqi Zhang, Danfei Xu, Ye Zhao
Task and Motion Planning (TAMP) integrates high-level task planning and low-level motion planning to equip robots with the autonomy to effectively reason over long-horizon, dynamic tasks.
no code implementations • 13 Feb 2024 • Shiqi Zhang, Zheng Qiu, Daiki Takeuchi, Noboru Harada, Shoji Makino
With the rapid development of neural networks in recent years, the ability of various networks to enhance the magnitude spectrum of noisy speech in the single-channel speech enhancement domain has become exceptionally outstanding.
no code implementations • 24 Sep 2023 • Kai Gao, Yan Ding, Shiqi Zhang, Jingjin Yu
Effectively performing object rearrangement is an essential skill for mobile manipulators, e. g., setting up a dinner table or organizing a desk.
no code implementations • 8 Sep 2023 • David Defazio, Eisuke Hirota, Shiqi Zhang
The controller ensures stable walking, and the force estimator enables the robot to respond to the external forces from the human.
1 code implementation • 27 May 2023 • Yan Ding, Xiaohan Zhang, Saeid Amiri, Nieqing Cao, Hao Yang, Andy Kaminski, Chad Esselink, Shiqi Zhang
Each situation corresponds to a state instance wherein a robot is potentially unable to complete a task using a solution that normally works.
1 code implementation • 22 Apr 2023 • Bo Liu, Yuqian Jiang, Xiaohan Zhang, Qiang Liu, Shiqi Zhang, Joydeep Biswas, Peter Stone
LLM+P takes in a natural language description of a planning problem, then returns a correct (or optimal) plan for solving that problem in natural language.
no code implementations • 13 Nov 2022 • Kishan Chandan, Jack Albertson, Shiqi Zhang
In human-robot collaboration domains, augmented reality (AR) technologies have enabled people to visualize the state of robots.
no code implementations • 4 Oct 2022 • Yan Ding, Xiaohan Zhang, Saeid Amiri, Nieqing Cao, Hao Yang, Chad Esselink, Shiqi Zhang
This paper introduces a novel algorithm (COWP) for open-world task planning and situation handling that dynamically augments the robot's action knowledge with task-oriented common sense.
no code implementations • 3 May 2022 • Wei Zhao, Shiqi Zhang, Bing Zhou, Bei Wang
The network proposes a data-driven weighted adjacency matrix generation method to compensate for real-time spatial dependencies not reflected by the predefined adjacency matrix.
no code implementations • 11 Apr 2022 • Jiahao Zhang, Shiqi Zhang, Guang Lin
This paper proposes a new dimension reduction framework based on rotated multi-fidelity Gaussian process regression and a Bayesian active learning scheme when the available precise observations are insufficient.
no code implementations • 7 Apr 2022 • Jiahao Zhang, Shiqi Zhang, Guang Lin
We propose a new multi-resolution autoencoder DeepONet model referred to as MultiAuto-DeepONet to deal with this difficulty with the aid of convolutional autoencoder.
no code implementations • 6 Apr 2022 • Jiahao Zhang, Shiqi Zhang, Guang Lin
We introduce three different models: continuous time, discrete time and hybrid models.
no code implementations • 21 Mar 2022 • Wei Zhao, Shiqi Zhang, Bing Zhou, Bei Wang
Existing methods are usually based on graph neural networks using predefined spatial adjacency graphs of traffic networks to model spatial dependencies, ignoring the dynamic correlation of relationships between road nodes.
no code implementations • 4 Mar 2022 • Shiqi Zhang, Zhongkui Li
In both cases, quantitative relationships among the parameters of the controllers, the Laplacian matrix of the network topology, and the robustness against aperiodic event triggering and frequency-domain uncertainties are unveiled.
no code implementations • 4 Mar 2022 • Shiqi Zhang, Zhongkui Li
It is revealed that in static or dynamic event triggering mechanisms, the sampling errors are images of affine operators acting on the sampled outputs.
no code implementations • 21 Feb 2022 • Saeid Amiri, Kishan Chandan, Shiqi Zhang
Robot planning in partially observable domains is difficult, because a robot needs to estimate the current state and plan actions at the same time.
no code implementations • 15 Feb 2022 • Christian Moya, Shiqi Zhang, Meng Yue, Guang Lin
This paper proposes a new data-driven method for the reliable prediction of power system post-fault trajectories.
no code implementations • 27 Jul 2021 • Hao Yang, Tavan Eftekhar, Chad Esselink, Yan Ding, Shiqi Zhang
Everyday tasks are characterized by their varieties and variations, and frequently are not clearly specified to service agents.
no code implementations • 23 Jul 2021 • David Defazio, Yohei Hayamizu, Shiqi Zhang
Could one use a formal language to specify quadruped gaits?
no code implementations • 7 Feb 2021 • Renchi Yang, Jieming Shi, Yin Yang, Keke Huang, Shiqi Zhang, Xiaokui Xiao
Given a graph G where each node is associated with a set of attributes, and a parameter k specifying the number of output clusters, k-attributed graph clustering (k-AGC) groups nodes in G into k disjoint clusters, such that nodes within the same cluster share similar topological and attribute characteristics, while those in different clusters are dissimilar.
no code implementations • 19 Aug 2020 • Shiqi Zhang, Mohan Sridharan
Reasoning with declarative knowledge (RDK) and sequential decision-making (SDM) are two key research areas in artificial intelligence.
no code implementations • SIGDIAL (ACL) 2020 • Keting Lu, Shiqi Zhang, Peter Stone, Xiaoping Chen
More interestingly, the robot was able to learn from navigation tasks to improve its dialog strategies.
no code implementations • SIGDIAL (ACL) 2020 • Yan Cao, Keting Lu, Xiaoping Chen, Shiqi Zhang
Reinforcement learning methods have been used to compute dialog policies from language-based interaction experiences.
no code implementations • 23 Apr 2020 • Yohei Hayamizu, Saeid Amiri, Kishan Chandan, Keiki Takadama, Shiqi Zhang
Reinforcement learning (RL) enables an agent to learn from trial-and-error experiences toward achieving long-term goals; automated planning aims to compute plans for accomplishing tasks using action knowledge.
no code implementations • 22 Apr 2020 • Keting Lu, Shiqi Zhang, Xiaoping Chen
First, we develop an algorithm, called Experience Grafting (EG), to enable RL agents to reorganize segments of the few high-quality trajectories from the experience pool to generate many synthetic trajectories while retaining the quality.
no code implementations • 18 Apr 2020 • Shiqi Zhang, Piyush Khandelwal, Peter Stone
Robot sequential decision-making in the real world is a challenge because it requires the robots to simultaneously reason about the current world state and dynamics, while planning actions to accomplish complex tasks.
no code implementations • 31 Jul 2019 • Yi Wang, Shiqi Zhang, Joohyung Lee
In this paper, we present a unified framework to integrate icorpp's reasoning and planning components.
no code implementations • 16 Jan 2019 • Saeid Amiri, Mohammad Shokrolah Shirazi, Shiqi Zhang
The key contribution of this work is a robot SDM framework, called LCORPP, that supports the simultaneous capabilities of supervised learning for passive state estimation, automated reasoning with declarative human knowledge, and planning under uncertainty toward achieving long-term goals.
no code implementations • 21 Nov 2018 • Yuqian Jiang, Fangkai Yang, Shiqi Zhang, Peter Stone
In the outer loop, the plan is executed, and the robot learns from the execution experience via model-free RL, to further improve its task-motion plans.
no code implementations • 28 Sep 2018 • Keting Lu, Shiqi Zhang, Peter Stone, Xiaoping Chen
In this work, we integrate logical-probabilistic KRR with model-based RL, enabling agents to simultaneously reason with declarative knowledge and learn from interaction experiences.
no code implementations • 20 Aug 2018 • Keting Lu, Shiqi Zhang, Xiaoping Chen
Reinforcement learning methods have been used for learning dialogue policies.
no code implementations • COLING 2018 • Shiqi Zhang, Deyi Xiong
In this paper, we propose a new sentence weighting method for the domain adaptation of neural machine translation.
no code implementations • 23 Apr 2018 • Yuqian Jiang, Shiqi Zhang, Piyush Khandelwal, Peter Stone
PDDL is designed for task planning, and PDDL-based planners are widely used for a variety of planning problems.
no code implementations • 17 Aug 2015 • Mohan Sridharan, Michael Gelfond, Shiqi Zhang, Jeremy Wyatt
This paper describes an architecture for robots that combines the complementary strengths of probabilistic graphical models and declarative programming to represent and reason with logic-based and probabilistic descriptions of uncertainty and domain knowledge.
no code implementations • 5 May 2014 • Shiqi Zhang, Mohan Sridharan, Michael Gelfond, Jeremy Wyatt
This paper describes an architecture that combines the complementary strengths of declarative programming and probabilistic graphical models to enable robots to represent, reason with, and learn from, qualitative and quantitative descriptions of uncertainty and knowledge.
no code implementations • 29 Jul 2013 • Shiqi Zhang, Mohan Sridharan
For widespread deployment in domains characterized by partial observability, non-deterministic actions and unforeseen changes, robots need to adapt sensing, processing and interaction with humans to the tasks at hand.