2 code implementations • 5 Apr 2024 • Zifu Wan, Yuhao Wang, Silong Yong, Pingping Zhang, Simon Stepputtis, Katia Sycara, Yaqi Xie
In this work, we introduce Sigma, a Siamese Mamba network for multi-modal semantic segmentation, utilizing the Selective Structured State Space Model, Mamba.
no code implementations • 26 Mar 2024 • Samuel Li, Sarthak Bhagat, Joseph Campbell, Yaqi Xie, Woojun Kim, Katia Sycara, Simon Stepputtis
Task-oriented grasping of unfamiliar objects is a necessary skill for robots in dynamic in-home environments.
1 code implementation • 24 Mar 2024 • Shreya Sharma, Dana Hughes, Katia Sycara
This paper describes CBGT-Net, a neural network model inspired by the cortico-basal ganglia-thalamic (CBGT) circuits found in mammalian brains.
1 code implementation • 19 Mar 2024 • Ce Zhang, Simon Stepputtis, Katia Sycara, Yaqi Xie
Recently, large-scale pre-trained Vision-Language Models (VLMs) have demonstrated great potential in learning open-world visual representations, and exhibit remarkable performance across a wide range of downstream tasks through efficient fine-tuning.
1 code implementation • 18 Mar 2024 • Ce Zhang, Simon Stepputtis, Joseph Campbell, Katia Sycara, Yaqi Xie
Being able to understand visual scenes is a precursor for many downstream tasks, including autonomous driving, robotics, and other vision-based approaches.
no code implementations • 13 Feb 2024 • Yu Quan Chong, Jiaoyang Li, Katia Sycara
To incorporate task assignment, path planning, and a user-defined objective into a coherent framework, this paper examines the Task Assignment and Path Finding with Precedence and Temporal Constraints (TAPF-PTC) problem.
1 code implementation • 14 Dec 2023 • Andrew Jong, Mukai Yu, Devansh Dhrafani, Siva Kailas, Brady Moon, Katia Sycara, Sebastian Scherer
We present the Wildland-fire Infrared Thermal (WIT-UAS) dataset for long-wave infrared sensing of crew and vehicle assets amidst prescribed wildland fire environments.
no code implementations • 14 Dec 2023 • Yafei Hu, Quanting Xie, Vidhi Jain, Jonathan Francis, Jay Patrikar, Nikhil Keetha, Seungchan Kim, Yaqi Xie, Tianyi Zhang, Shibo Zhao, Yu Quan Chong, Chen Wang, Katia Sycara, Matthew Johnson-Roberson, Dhruv Batra, Xiaolong Wang, Sebastian Scherer, Zsolt Kira, Fei Xia, Yonatan Bisk
Motivated by the impressive open-set performance and content generation capabilities of web-scale, large-capacity pre-trained models (i. e., foundation models) in research fields such as Natural Language Processing (NLP) and Computer Vision (CV), we devote this survey to exploring (i) how these existing foundation models from NLP and CV can be applied to the field of robotics, and also exploring (ii) what a robotics-specific foundation model would look like.
no code implementations • 13 Dec 2023 • Huao Li, Yao Fan, Keyang Zheng, Michael Lewis, Katia Sycara
Our proposed approach is agnostic to task environment and RL model structure, therefore has the potential to be generalized to a wide range of applications.
no code implementations • 30 Nov 2023 • Renos Zabounidis, Ini Oguntola, Konghao Zhao, Joseph Campbell, Simon Stepputtis, Katia Sycara
Concept bottleneck models (CBMs) are interpretable models that first predict a set of semantically meaningful features, i. e., concepts, from observations that are subsequently used to condition a downstream task.
no code implementations • 29 Nov 2023 • Xijia Zhang, Yue Guo, Simon Stepputtis, Katia Sycara, Joseph Campbell
Intelligent agents such as robots are increasingly deployed in real-world, safety-critical settings.
no code implementations • 9 Nov 2023 • Simon Stepputtis, Joseph Campbell, Yaqi Xie, Zhengyang Qi, Wenxin Sharon Zhang, Ruiyi Wang, Sanketh Rangreji, Michael Lewis, Katia Sycara
We discuss the capabilities of LLMs to utilize deceptive long-horizon conversations between six human players to determine each player's goal and motivation.
no code implementations • 16 Oct 2023 • Huao Li, Yu Quan Chong, Simon Stepputtis, Joseph Campbell, Dana Hughes, Michael Lewis, Katia Sycara
While Large Language Models (LLMs) have demonstrated impressive accomplishments in both reasoning and planning, their abilities in multi-agent collaborations remains largely unexplored.
no code implementations • 19 Sep 2023 • Xijia Zhang, Yue Guo, Simon Stepputtis, Katia Sycara, Joseph Campbell
Intelligent agents such as robots are increasingly deployed in real-world, safety-critical settings.
no code implementations • 12 Sep 2023 • Sarthak Bhagat, Simon Stepputtis, Joseph Campbell, Katia Sycara
This work focuses on anticipating long-term human actions, particularly using short video segments, which can speed up editing workflows through improved suggestions while fostering creativity by suggesting narratives.
no code implementations • 3 Jul 2023 • Ini Oguntola, Joseph Campbell, Simon Stepputtis, Katia Sycara
The ability to model the mental states of others is crucial to human social intelligence, and can offer similar benefits to artificial agents with respect to the social dynamics induced in multi-agent settings.
1 code implementation • 2 Jul 2023 • Yimin Tang, Zhongqiang Ren, Jiaoyang Li, Katia Sycara
As a leading approach to address TAPF, Conflict-Based Search with Target Assignment (CBS-TA) leverages both K-best target assignments to create multiple search trees and Conflict-Based Search (CBS) to resolve collisions in each search tree.
no code implementations • 21 Jun 2023 • Joseph Campbell, Yue Guo, Fiona Xie, Simon Stepputtis, Katia Sycara
Transfer learning can be applied in deep reinforcement learning to accelerate the training of a policy in a target task by transferring knowledge from a policy learned in a related source task.
1 code implementation • 15 Jun 2023 • Sarthak Bhagat, Simon Stepputtis, Joseph Campbell, Katia Sycara
Despite the advances made in visual object recognition, state-of-the-art deep learning models struggle to effectively recognize novel objects in a few-shot setting where only a limited number of examples are provided.
no code implementations • 28 Feb 2023 • Seth Karten, Siva Kailas, Huao Li, Katia Sycara
Explicit communication among humans is key to coordinating and learning.
no code implementations • 23 Feb 2023 • Renos Zabounidis, Joseph Campbell, Simon Stepputtis, Dana Hughes, Katia Sycara
Multi-agent robotic systems are increasingly operating in real-world environments in close proximity to humans, yet are largely controlled by policy models with inscrutable deep neural network representations.
no code implementations • 10 Feb 2023 • Yuzhe Lu, Zhenlin Wang, Runtian Zhai, Soheil Kolouri, Joseph Campbell, Katia Sycara
Out-of-distribution (OOD) data poses serious challenges in deployed machine learning models as even subtle changes could incur significant performance drops.
no code implementations • 30 Nov 2022 • Seth Karten, Mycal Tucker, Siva Kailas, Katia Sycara
We evaluate the learned communication `language' through direct causal analysis of messages in non-sparse runs to determine the range of lossless sparse budgets, which allow zero-shot sparsity, and the range of sparse budgets that will inquire a reward loss, which is minimized by our learned gating function with few-shot sparsity.
1 code implementation • 15 Nov 2022 • Yue Guo, Joseph Campbell, Simon Stepputtis, Ruiyu Li, Dana Hughes, Fei Fang, Katia Sycara
This allows the student to self-reflect on what it has learned, enabling advice generalization and leading to improved sample efficiency and learning performance - even in environments where the teacher is sub-optimal.
Multi-agent Reinforcement Learning reinforcement-learning +2
no code implementations • 5 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.
no code implementations • 26 Jan 2022 • Mycal Tucker, William Kuhl, Khizer Shahid, Seth Karten, Katia Sycara, Julie Shah
Neural nets are powerful function approximators, but the behavior of a given neural net, once trained, cannot be easily modified.
no code implementations • 19 Jan 2022 • Seth Karten, Mycal Tucker, Huao Li, Siva Kailas, Michael Lewis, Katia Sycara
In human-agent teams tested in benchmark environments, where agents have been modeled using the Enforcers, we find that a prototype-based method produces meaningful discrete tokens that enable human partners to learn agent communication faster and better than a one-hot baseline.
no code implementations • NeurIPS 2021 • Mycal Tucker, Huao Li, Siddharth Agrawal, Dana Hughes, Katia Sycara, Michael Lewis, Julie Shah
Neural agents trained in reinforcement learning settings can learn to communicate among themselves via discrete tokens, accomplishing as a team what agents would be unable to do alone.
1 code implementation • 31 Jul 2021 • Vidhi Jain, Prakhar Agarwal, Shishir Patil, Katia Sycara
We know that humans can search for an object like a book, or a plate in an unseen house, based on the spatial semantics of bigger objects detected.
no code implementations • 7 Apr 2021 • Ini Oguntola, Dana Hughes, Katia Sycara
When developing AI systems that interact with humans, it is essential to design both a system that can understand humans, and a system that humans can understand.
no code implementations • 7 Mar 2021 • Tianwei Ni, Huao Li, Siddharth Agrawal, Suhas Raja, Fan Jia, Yikang Gui, Dana Hughes, Michael Lewis, Katia Sycara
Previous human-human team research have shown complementary policies in TSF game and diversity in human players' skill, which encourages us to relax the assumptions on human policy.
no code implementations • 15 Nov 2020 • Vidhi Jain, Rohit Jena, Huao Li, Tejus Gupta, Dana Hughes, Michael Lewis, Katia Sycara
In our efforts to model the rescuer's mind, we begin with a simple simulated search and rescue task in Minecraft with human participants.
1 code implementation • 20 Sep 2020 • Rohit Jena, Siddharth Agrawal, Katia Sycara
Generative Adversarial Imitation Learning suffers from the fundamental problem of reward bias stemming from the choice of reward functions used in the algorithm.
no code implementations • 4 Aug 2020 • Xinzhi Wang, Huao Li, HUI ZHANG, Michael Lewis, Katia Sycara
The results show that verbal explanation generated by both models improve subjective satisfaction of users towards the interpretability of DRL systems.
1 code implementation • 6 Jul 2020 • Ankur Deka, Katia Sycara
We corroborate that modeling agents with Graph Neural Networks and training them with Reinforcement Learning leads to the evolution of increasingly complex strategies for each team.
1 code implementation • 10 Apr 2020 • Rohit Jena, Shirsendu Sukanta Halder, Katia Sycara
Despite the recent developments in vision-related problems using deep neural networks, there still remains a wide scope in the improvement of generalizing these models to unseen examples.
2 code implementations • 21 Jan 2020 • Rohit Jena, Changliu Liu, Katia Sycara
Behavior cloning and GAIL are two widely used methods for performing imitation learning.
no code implementations • 24 Dec 2019 • Rahul Radhakrishnan Iyer, Yulong Pei, Katia Sycara
Tweet classification has attracted considerable attention recently.
no code implementations • 13 Dec 2019 • Rahul Radhakrishnan Iyer, Katia Sycara
With the increasing growth of social media, people have started relying heavily on the information shared therein to form opinions and make decisions.
no code implementations • 11 Dec 2019 • Rahul Radhakrishnan Iyer, Ronghuo Zheng, Yuezhang Li, Katia Sycara
In this work, we investigate whether crowd wisdom is useful in predicting such outcomes and whether their opinions are influenced by the experts in the field.
no code implementations • 11 Nov 2019 • Swaminathan Gurumurthy, Sumit Kumar, Katia Sycara
Meta-Reinforcement learning approaches aim to develop learning procedures that can adapt quickly to a distribution of tasks with the help of a few examples.
4 code implementations • 4 Jun 2019 • Akshat Agarwal, Sumit Kumar, Katia Sycara
While multi-agent interactions can be naturally modeled as a graph, the environment has traditionally been considered as a black box.
1 code implementation • 21 Jan 2019 • Sumit Kumar, Wenhao Luo, George Kantor, Katia Sycara
A looming question that must be solved before robotic plant phenotyping capabilities can have significant impact to crop improvement programs is scalability.
1 code implementation • 24 Sep 2018 • Akshat Agarwal, Abhinau Kumar V, Kyle Dunovan, Erik Peterson, Timothy Verstynen, Katia Sycara
The agent makes no decision by default, and the burden of proof to make a decision falls on the policy to accrue evidence strongly in favor of a single decision.
no code implementations • 17 Sep 2018 • Yuezhang Li, Katia Sycara, Rahul Iyer
In this paper, we propose a novel method that can incorporate object recognition processing to deep reinforcement learning models.
1 code implementation • 17 Sep 2018 • Rahul Iyer, Yuezhang Li, Huao Li, Michael Lewis, Ramitha Sundar, Katia Sycara
For those systems to be accepted and trusted, the users should be able to understand the reasoning process of the system, i. e. the system should be transparent.
1 code implementation • 15 Sep 2018 • Raghuram Mandyam Annasamy, Katia Sycara
Deep reinforcement learning techniques have demonstrated superior performance in a wide variety of environments.
1 code implementation • 6 Sep 2018 • Akshat Agarwal, Ryan Hope, Katia Sycara
Research in deep reinforcement learning (RL) has coalesced around improving performance on benchmarks like the Arcade Learning Environment.
Ranked #1 on Space Fortress on Autoturn
1 code implementation • 10 Aug 2018 • Akshat Agarwal, Swaminathan Gurumurthy, Vasu Sharma, Mike Lewis, Katia Sycara
The task of conducting visually grounded dialog involves learning goal-oriented cooperative dialog between autonomous agents who exchange information about a scene through several rounds of questions and answers in natural language.
no code implementations • 12 Jun 2018 • Sreecharan Sankaranarayanan, Raghuram Mandyam Annasamy, Katia Sycara, Carolyn Penstein Rosé
Q-Ensembles are a model-free approach where input images are fed into different Q-networks and exploration is driven by the assumption that uncertainty is proportional to the variance of the output Q-values obtained.
1 code implementation • 17 May 2018 • Akshat Agarwal, Ryan Hope, Katia Sycara
Although there has been remarkable progress and impressive performance on reinforcement learning (RL) on Atari games, there are many problems with challenging characteristics that have not yet been explored in Deep Learning for RL.
no code implementations • COLING 2016 • Yuezhang Li, Ronghuo Zheng, Tian Tian, Zhiting Hu, Rahul Iyer, Katia Sycara
Due to the lack of structured knowledge applied in learning distributed representation of cate- gories, existing work cannot incorporate category hierarchies into entity information.
no code implementations • 12 May 2016 • Yuezhang Li, Ronghuo Zheng, Tian Tian, Zhiting Hu, Rahul Iyer, Katia Sycara
Due to the lack of structured knowledge applied in learning distributed representation of categories, existing work cannot incorporate category hierarchies into entity information.~We propose a framework that embeds entities and categories into a semantic space by integrating structured knowledge and taxonomy hierarchy from large knowledge bases.