Julio Godoy

Exploiting Spatial Locality and Heterogeneity of Agents for Search and Rescue Teamwork

We propose coordination mechanisms for multiple heterogeneous physical agents that operate in city-scale disaster scenarios, where they need to find and rescue people and extinguish fires. Large-scale disasters are characterized by limited and unreliable communications; dangerous events that may disable agents; uncertainty about the location, duration, and type of tasks; and stringent temporal constraints on task completion times. In our approach, agents form teams with other agents that are in the same geographical area. Our algorithms either yield stable teams formed up front and never change, fluid teams where agents can change teams as need arises, or teams that restrict the types of agents that can belong to the same team. We compare our teaming algorithms against a baseline algorithm in which agents operate independently of others and two state-of-the-art coordination mechanisms. Our algorithms are tested in city-scale disaster simulations using the RoboCup Rescue simulator. Our experiments with different city maps show that, in general, forming teams leads to increased task completion and, specifically, that our teaming method that restricts the types of agents in a team outperforms the other methods.

Stochastic Tree Search with Useful Cycles for patrolling problems

An autonomous robot team can be employed for continuous and strategic coverage of arbitrary environments for different missions. In this work, we propose an anytime approach for creating multi-robot patrolling policies. Our approach involves a novel extension of Monte Carlo Tree Search (MCTS) to allow robots to have life-long, cyclic policies so as to provide continual coverage of an environment. Our proposed method can generate near-optimal policies for a team of robots for small environments in real-time (and in larger environments in under a minute). By incorporating additional planning heuristics we are able to plan coordinated patrolling paths for teams of several robots in large environments quickly on commodity hardware.

Task allocation for spatially and temporally distributed tasks

In multi robot task allocation, a set of tasks has to be allocated to a group of robots while optimizing some measure (for example, fuel or time). In order to find the optimal allocation, an exponential number of possibilities must be explored. In this work, we extend the Consensus Based Bundle Algorithm, to improve its support for tasks with time constraints. The modified algorithm is compared with the original one in order to show how strategic modifications to the algorithm increase the number of tasks successfully completed.

Geo-referencing with semi-automatic gazetteer expansion using lexico-syntactical patterns and co-reference analysis

Geo-referencing is a key task for geographical information retrieval because it allows unstructured or textual documents (i.e., Web pages) to be associated with geographical locations, which are then used by geo-search engines to index documents and search information by spatial criteria. This work proposes a strategy to extract geo-references from textual documents that combine natural language-processing techniques and co-reference solving heuristics, which in turn can be used to expand a geographical gazetteer. Implicit geographical entities (i.e., those entities referred to by pronouns) are recognized and incorporated into the gazetteer that is updated and used for geo-referencing tasks. Experiments show the promise of the approach to geo-referencing Web pages when dealing with implicit and/or indirect geo-references.

ALAN: adaptive learning for multi-agent navigation

In multi-agent navigation, agents need to move towards their goal locations while avoiding collisions with other agents and obstacles, often without communication. Existing methods compute motions that are locally optimal but do not account for the aggregated motions of all agents, producing inefficient global behavior especially when agents move in a crowded space. In this work, we develop a method that allows agents to dynamically adapt their behavior to their local conditions. We formulate the multi-agent navigation problem as an action-selection problem and propose an approach, ALAN, that allows agents to compute time-efficient and collision-free motions. ALAN is highly scalable because each agent makes its own decisions on how to move, using a set of velocities optimized for a variety of navigation tasks. Experimental results show that agents using ALAN, in general, reach their destinations faster than using ORCA, a state-of-the-art collision avoidance framework, and two other navigation models.