Search By Subject

In this work we explore the use of latent representations obtained from multiple input sensory modalities (such as images or sounds) in allowing an agent to learn and exploit policies over different subsets of input modalities. We propose a three-stage ...

We assume that service robots will have spare time in between scheduled user requests, which they could use to perform additional unrequested services in order to learn a model of users' preferences and receive reward. However, a mobile service robot is ...

We present a method for doing zero-shot transfer of multi-agent policies as the number of teammates, opponents, and environment size varies. We apply our approach to RoboCup inspired test domains, where it is necessary for policies to adapt to changing ...

Pepper is a humanoid robot, specifically designed for social interaction, that has been deployed in a variety of public environments. A programmable version of Pepper is also available, enabling our focused research on perception and behavior robustness ...

Automated data collection in urban transportation systems produces a large volume of passenger data. However, quite a few of the data are still incomplete, limiting the insight into passenger mobility. The unavailability of destination information in ...

There are many tasks that humans perform that involve observing video streams, as well as tracking objects or quantities related to the events depicted in the video, that can be made more transparent by the addition of appropriate drawings to a video, ...

Several research efforts address the challenge of having users incrementally teach or demonstrate a task to a robot. We are interested in an autonomous robot that persists over time and the problem of teaching it an additional task. We believe that the ...

Making decisions based on accurate models enables robots to exploit domain knowledge to act intelligently. However, in many realistic domains, it is impossible to have globally accurate models, as the world may exhibit modes of behavior during ...

AI is becoming pervasive in our lives. Its impact on society is increasing every day. Its potential is enormous and there have recently been several outstanding achievements.

In order for an autonomous service robot to provide the best service possible for its users, it must have a considerable amount of knowledge of the environment in which it operates. Service robots perform requests for users and can learn information ...

Ridesharing services have the potential to fill empty seats in cars, reduce emissions and enable more efficient transportation. We propose rideshare services which transfer passengers between multiple drivers. By planning for transfers, we increase the ...

Autonomous mobile service robots navigate in their environments in order to perform tasks requested by users. We envision service robots learning about their environment by scheduling exploration tasks in which they seek out new knowledge and using this ...

This paper presents a novel formulation for the problem of finding objects in a known environment while minimizing the search cost. Our approach consists in formalizing this class of problems as Stochastic Shortest Path (SSP) problems, a decision-...

Robots are becoming increasingly modular in their design, allowing different configurations of hardware and software, e.g., different wheels, sensors, and algorithms. We are interested in forming a multi-robot team by configuring each robot (i.e., ...

As robots are introduced into human environments for long periods of time, human owners and collaborators will expect them to remember shared events that occur during execution. Beyond naturalness of having memories about recent and longer-term ...

This paper describes an algorithm that enables a mobile robot to find an arbitrary object and take it to a destination location. Previous approaches have been able to search for a fixed set of objects. In contrast, our approach is able to dynamically ...

Many robot dances are preprogrammed by choreographers for a particular piece of music so that the motions can be smoothly executed and synchronized to the music. We are interested in automating the task of robot dance choreography to allow robots to ...

We formally present the Mutual State Capability-Based Role Assignment (MuSCRA) model, as we introduce that an agent, acting in a team, has capabilities that depend not only on its own individual skills, but also on its teammates and their mutual state. ...

In a heterogeneous team, agents have different capabilities with regards to the actions relevant to the task. Roles are typically assigned to individual agents in such a team, where each role is responsible for a certain aspect of the joint team goal. ...