Author name cluster

Felix Duvallet

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

IJCAI Conference 2016 Conference Paper

Learning Qualitative Spatial Relations for Robotic Navigation

Abdeslam Boularias
Felix Duvallet
Jean Oh
Anthony Stentz

We consider the problem of robots following natural language commands through previously unknown outdoor environments. A robot receives commands in natural language, such as Navigate around the building to the car left of the fire hydrant and near the tree. The robot needs first to classify its surrounding objects into categories, using images obtained from its sensors. The result of this classification is a map of the environment, where each object is given a list of semantic labels, such as tree or car, with varying degrees of confidence. Then, the robot needs to ground the nouns in the command, i. e. , mapping each noun in the command into a physical object in the environment. The robot needs also to ground a specified navigation mode, such as navigate quickly or navigate covertly, as a cost map. In this work, we show how to ground nouns and navigation modes by learning from examples demonstrated by humans.

PDF Details

ICRA Conference 2015 Conference Paper

Grounding spatial relations for outdoor robot navigation

Abdeslam Boularias
Felix Duvallet
Jean Oh
Anthony Stentz

We propose a language-driven navigation approach for commanding mobile robots in outdoor environments. We consider unknown environments that contain previously unseen objects. The proposed approach aims at making interactions in human-robot teams natural. Robots receive from human teammates commands in natural language, such as “Navigate around the building to the car left of the fire hydrant and near the tree”. A robot needs first to classify its surrounding objects into categories, using images obtained from its sensors. The result of this classification is a map of the environment, where each object is given a list of semantic labels, such as “tree” and “car”, with varying degrees of confidence. Then, the robot needs to ground the nouns in the command. Grounding, the main focus of this paper, is mapping each noun in the command into a physical object in the environment. We use a probabilistic model for interpreting the spatial relations, such as “left of” and “near”. The model is learned from examples provided by humans. For each noun in the command, a distribution on the objects in the environment is computed by combining spatial constraints with a prior given as the semantic classifier's confidence values. The robot needs also to ground the navigation mode specified in the command, such as “navigate quickly” and “navigate covertly”, as a cost map. The cost map is also learned from examples, using Inverse Optimal Control (IOC). The cost map and the grounded goal are used to generate a path for the robot. This approach is evaluated on a robot in a real-world environment. Our experiments clearly show that the proposed approach is efficient for commanding outdoor robots.

Details

ICRA Conference 2015 Conference Paper

Learning models for following natural language directions in unknown environments

Sachithra Hemachandra
Felix Duvallet
Thomas M. Howard
Nicholas Roy
Anthony Stentz
Matthew R. Walter

Natural language offers an intuitive and flexible means for humans to communicate with the robots that we will increasingly work alongside in our homes and workplaces. Recent advancements have given rise to robots that are able to interpret natural language manipulation and navigation commands, but these methods require a prior map of the robot's environment. In this paper, we propose a novel learning framework that enables robots to successfully follow natural language route directions without any previous knowledge of the environment. The algorithm utilizes spatial and semantic information that the human conveys through the command to learn a distribution over the metric and semantic properties of spatially extended environments. Our method uses this distribution in place of the latent world model and interprets the natural language instruction as a distribution over the intended behavior. A novel belief space planner reasons directly over the map and behavior distributions to solve for a policy using imitation learning. We evaluate our framework on a voice-commandable wheelchair. The results demonstrate that by learning and performing inference over a latent environment model, the algorithm is able to successfully follow natural language route directions within novel, extended environments.

Details

AAAI Conference 2015 Conference Paper

Toward Mobile Robots Reasoning Like Humans

Jean Oh
Arne Suppé
Felix Duvallet
Abdeslam Boularias
Luis Navarro-Serment
Martial Hebert
Anthony Stentz
Jerry Vinokurov

Robots are increasingly becoming key players in human-robot teams. To become effective teammates, robots must possess profound understanding of an environment, be able to reason about the desired commands and goals within a speciﬁc context, and be able to communicate with human teammates in a clear and natural way. To address these challenges, we have developed an intelligence architecture that combines cognitive components to carry out high-level cognitive tasks, semantic perception to label regions in the world, and a natural language component to reason about the command and its relationship to the objects in the world. This paper describes recent developments using this architecture on a ﬁelded mobile robot platform operating in unknown urban environments. We report a summary of extensive outdoor experiments; the results suggest that a multidisciplinary approach to robotics has the potential to create competent human-robot teams.

PDF Details

ICRA Conference 2013 Conference Paper

Imitation learning for natural language direction following through unknown environments

Felix Duvallet
Thomas Kollar
Anthony Stentz

The use of spoken instructions in human-robot teams holds the promise of enabling untrained users to effectively control complex robotic systems in a natural and intuitive way. Providing robots with the capability to understand natural language directions would enable effortless coordination in human robot teams that operate in non-specialized unknown environments. However, natural language direction following through unknown environments requires understanding the meaning of language, using a partial semantic world model to generate actions in the world, and reasoning about the environment and landmarks that have not yet been detected. We address the problem of robots following natural language directions through complex unknown environments. By exploiting the structure of spatial language, we can frame direction following as a problem of sequential decision making under uncertainty. We learn a policy which predicts a sequence of actions that follow the directions by exploring the environment and discovering landmarks, backtracking when necessary, and explicitly declaring when it has reached the destination. We use imitation learning to train the policy, using demonstrations of people following directions. By training explicitly in unknown environments, we can generalize to situations that have not been encountered previously.

Details

IROS Conference 2010 Conference Paper

Imitation learning for task allocation

Felix Duvallet
Anthony Stentz

At the heart of multi-robot task allocation lies the ability to compare multiple options in order to select the best. In some domains this utility evaluation is not straightforward, for example due to complex and unmodeled underlying dynamics or an adversary in the environment. Explicitly modeling these extrinsic influences well enough so that they can be accounted for in utility computation (and thus task allocation) may be intractable, but a human expert may be able to quickly gain some intuition about the form of the desired solution. We propose to harness the expert's intuition by applying imitation learning to the multi-robot task allocation domain. Using a market-based method, we steer the allocation process by biasing prices in the market according to a policy which we learn using a set of demonstrated allocations (the expert's solutions to a number of domain instances). We present results in two distinct domains: a disaster response scenario where a team of agents must put out fires that are spreading between buildings, and an adversarial game in which teams must make complex strategic decisions to score more points than their opponents.

Details

IROS Conference 2008 Conference Paper

WiFi position estimation in industrial environments using Gaussian processes

Felix Duvallet
Ashley Tews

The increased popularity of wireless networks has enabled the development of localization techniques that rely on WiFi signal strength. These systems are cheap, effective, and require no modifications to the environment. In this paper, we present a WiFi localization algorithm that generates WiFi maps using Gaussian process regression, and then estimates the global position of an autonomous vehicle in an industrial environment using a particle filter. This estimate can be used for bootstrapping a higher-resolution localizer, or for cross-checking and localization redundancy. The system has been designed to operate both indoors and outdoors, using only the existing wireless infrastructure. It has been integrated with an existing laser-beacon localizer to aid during initialization and for recovery after a failure. Experiments conducted at an industrial site using a large forklift-type autonomous vehicle are presented.

Details

ICRA Conference 2006 Conference Paper

Fun with Robots: a Student-taught Undergraduate Robotics Course

Steven V. Shamlian
Katherine Killfoile
Ryan A. Kellogg
Felix Duvallet

We present a lab-based, student-taught robotics course at Carnegie Mellon University entitled Fun With Robots. The course does not require background knowledge of robotics, and students enroll from a wide variety of disciplines and education levels. Fun With Robots increases interest in robotics, and emphasizes the highly multidisciplinary nature of the field. In the course, students build a robot and learn basic elements of microcontroller programming, sensor use, planning, and manipulation through engaging projects. Fun With Robots is constantly evolving and has changed significantly over the six semesters it has been taught. This course serves as an introduction to robotics for students new to the field and links high school programs and advanced undergraduate robotics courses. Foremost, the course is intended to be fun; students are encouraged to demonstrate creativity and self-expression. Course materials are available via the web at http://www.funwithrobots.org

Details