        |
 |
|
|||
|
|
 |
|
I am a PhD student in the Department of Computer Science working with Dr. Nancy Amato. My work is focused on motion planning alogirthms and the simulation of muti-agent group behavior. We investigate how agents can work cooperatively to perform tasks, plan paths in dynamic environments, or influence another group of agents to locations in an environment.
| CV (ps, pdf) |
 |
A Framework for Planning Motion in Environments with Moving Obstacles
We present a heuristic approach to planning in an environment with moving obstacles. Our approach assumes that the robot has no knowledge of the future trajectory of the moving objects. Our framework also distinguishes between two types of moving objects:hard and soft objects in the environment. We distinguish between the two types of objects in the environment as varying application domains could allow for some collision between moving objects. |
 |
Generation and Evaluation of Roadmap-Based Group Behaviors
We explore the benefits of integrating roadmap-based path planning methods with agents performing group behaviors to achieve different objectives. We show how a wide range of group behaviors can be facilitated by using dynamic roadmaps. We focus on two aspects of the adaptive approach to behavior generation. First, we propose a variety of seaching and hiding group behaviors. The behaviors we propose use an underlying roadmap which will be described more later. Although not all of these behaviors can be considered the most effective, there can be applications where each behavior can be useful. Secondly, we focus on how these behaviors can be evaluated. The evaluation of a behavior that a group of agents are executing can depend on the objective the agents are trying to achieve. |
 |
Specialized Techniques for Shepherding Behaviors
Shepherding behaviors are a type of flocking behavior in which outside agents guide or control members of a flock. Shepherding behaviors can be found in various forms in nature. In this work, we investigate ways to simulate these types of behaviors. When the size of the flock gets large or if the flock's behavior makes it difficult to influence, a single shepherd cannot adequately control the flock. In this work, we study how a group of shepherds can work cooperatively without communication to efficiently control the flock. |
 |
RESAMPL: A Region-Sensitive Adaptive Motion Planner
In this work, we present RESAMPL, a motion planning strategy that uses local region information to make intelligent decisions about how and where to sample, which samples to connect together, and to find paths through the environment. RESAMPL classifies regions based on the entropy of the samples in it, and then uses these classifications to further refine the sampling. Regions are placed in a region graph that encodes relationships between regions, e.g., edges correspond to overlapping regions. The strategy for connecting samples is guided by the region graph, and can be exploited in both multi-query and single-query scenarios. Our experimental results comparing RESAMPL to previous multi-query and single-query methods show that RESAMPL is generally significantly faster and also usually requires fewer samples to solve the problem. |
 |
Obstacle-Based Rapdily-Exploring Random Tree (OBRRT)
Here we present a new variant of Rapidly-Exploring Random Tree (RRT) path planning algorithm that explores narrow passages or difficult areas more effectively. We show that both workspace obstacle information and C-space information can help decide which direction to grow. The method includes many ways to grow the tree, some taking into account the obstacles in the environment. Using obstacle hints for directions to grow a tree for path planning can be beneficial, especially when exploring difficult areas. Indeed, whereas the standard RRT can face difficulties planning in a narrow passage, the tree based planner presented here works best in these areas. |
 |
Feature-Sensitive Motion Planning
In this work, we propose a feature-sensitive meta-planner that cooperatively applies more specialized planners to map an specific instance. It analyzes a region to characterize it so to find the best-suited planning strategy for the region and to decide whether it needs to partition it and repeat the characterization until assigning a planning strategy to each distinct region in the planning space. Then, the meta-planner maps each region with the strategy assigned. Finally, regional maps are combined into a map for the overall problem. |