An official website of the United States government
In open multiagent systems, the set of agents operating in the environment changes over time and in ways that are nontrivial to predict. For example, if collaborative robots were tasked with fighting wildfires, they may run out of suppressants and be temporarily unavailable to assist their peers. Because an agent’s optimal action depends on the actions of others, each agent must not only predict the actions of its peers, but, before that, reason whether they are even present to perform an action. Addressing openness thus requires agents to model each other’s presence, which can be enhanced through agents communicating about their presence in the environment. At the same time, communicative acts can also incur costs (e.g., consuming limited bandwidth), and thus an agent must tradeoff the benefits of enhanced coordination with the costs of communication. We present a new principled, decision-theoretic method in the context provided by the recent communicative interactive POMDP framework for planning in open agent settings that balances this tradeoff. Simulations of multiagent wildfire suppression problems demonstrate how communication can improve planning in open agent environments, as well as how agents tradeoff the benefits and costs of communication under different scenarios.
more »
« less
Agent-Environment Network for Temporal Action Proposal Generation
Temporal action proposal generation is an essential and challenging task that aims at localizing temporal intervals containing human actions in untrimmed videos. Most of existing approaches are unable to follow the human cognitive process of understanding the video context due to lack of attention mechanism to express the concept of an action or an agent who performs the action or the interaction between the agent and the environment. Based on the action definition that a human, known as an agent, interacts with the environment and performs an action that affects the environment, we propose a contextual Agent-Environment Network. Our proposed contextual AEN involves (i) agent pathway, operating at a local level to tell about which humans/agents are acting and (ii) environment pathway operating at a global level to tell about how the agents interact with the environment. Comprehensive evaluations on 20-action THUMOS-14 and 200- action ActivityNet-1.3 datasets with different backbone networks, i.e C3D and SlowFast, show that our method robustly exhibits outperformance against state-of-the-art methods regardless of the employed backbone network.
more »
« less
- Award ID(s):
- 1946391
- PAR ID:
- 10321624
- Date Published:
- Journal Name:
- ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
In open multiagent systems, the set of agents operating in the environment changes over time and in ways that are nontrivial to predict. For example, if collaborative robots were tasked with fighting wildfires, they may run out of suppressants and be temporarily unavailable to assist their peers. Because an agent's optimal action depends on the actions of others, each agent must not only predict the actions of its peers, but, before that, reason whether they are even present to perform an action. Addressing openness thus requires agents to model each other’s presence, which can be enhanced through agents communicating about their presence in the environment. At the same time, communicative acts can also incur costs (e.g., consuming limited bandwidth), and thus an agent must tradeoff the benefits of enhanced coordination with the costs of communication. We present a new principled, decision-theoretic method in the context provided by the recent communicative interactive POMDP framework for planning in open agent settings that balances this tradeoff. Simulations of multiagent wildfire suppression problems demonstrate how communication can improve planning in open agent environments, as well as how agents tradeoff the benefits and costs of communication under different scenarios.more » « less
-
This research investigated human performance in response to task demands that may be used to convey information about the human to an artificial agent. We performed an experiment with a dynamic time-sharing task to investigate participants development of temporal awareness of the task event unfolding in time. Temporal awareness as an extension, or a special case, of situation awareness, may provide for useful measures of covert mental models applicable to numerous tasks and for input to human-aware AI agents. Temporal awareness measures may be used to classify human performance into the control modes in the contextual control model (COCOM): scrambled, opportunistic, tactical, and strategic. Twenty-one participants participated in a within subjects experiment with an abstract task of resetting four independent timers within their respective windows of opportunity. The results show that temporal measures of task performance are sensitive to changes in task disruptions and difficulty and therefore have promise for human-aware AI.more » « less
-
Inspired by the recent problems in supply chains, we propose an approach to declarative modeling of contracts between agents that will eventually support reasoning about resilience of and about ways to improve supply chains. Specifically, we present a high-level language for specifying and reasoning about contracts over action domains of agents. We assume that the behavior of the agents can be formally expressed through action theories and view a contract as a collection of constraints. Each constraint specifies the responsibility of an agent to achieve a certain result by a deadline. Each agent also has a mapping between constraints and the agent’s concerns, i.e. issues that the agent is concerned about, which are modeled in accordance with the CPS Framework proposed by the National Institute of Standards and Technology. We discuss how common questions related to the fulfillment of a contract or the concerns of the agents can be answered and computed via Answer Set Programming.more » « less
-
Multi-agent systems (MASs) consisting of a number of autonomous agents that communicate, coordinate, and jointly sense the environment to achieve complex missions can be found in a variety of applications such as robotics, smart cities, and internet-of-things applications. Modeling and monitoring MAS requirements to guarantee overall mission objectives, safety, and reliability is an important problem. Such requirements implicitly require reasoning about diverse sensing and communication modalities between agents, analysis of the dependencies between agent tasks, and the spatial or virtual distance between agents. To capture such rich MAS requirements, we model agent interactions via multiple directed graphs, and introduce a new logic –Spatio-Temporal Logic with Graph Operators(STL-GO). The key innovation in STL-GO are graph operators that enable us to reason about the number of agents along either the incoming or outgoing edges of the underlying interaction graph that satisfy a given property of interest; for example, the requirement that an agent should sense at least two neighboring agents whose task graphs indicate the ability to collaborate. We then propose novel distributed monitoring conditions for individual agents that use only local information to determine whether or not an STL-GO specification is satisfied. We compare the expressivity of STL-GO against existing spatio-temporal logic formalisms, and demonstrate the utility of STL-GO and our distributed monitors in a bike-sharing and a multi-drone case study.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/icassp39728.2021.9415101
