skip to main content

Title: Opportunistic Multi-Robot Environmental Sampling via Decentralized Markov Decision Processes
We study the problem of information sampling with a group of mobile robots from an unknown environment. Each robot is given a unique region in the environment for the sampling task. The objective of the robots is to visit a subset of locations in the environment such that the collected information is maximized, and consequently, the underlying information model matches as close to reality as possible. The robots have limited communication ranges, and therefore can only communicate when nearby one another. The robots operate in a stochastic environment and their control uncertainty is handled using factored Decentralized Markov Decision Processes (Dec-MDP). When two or more robots communicate, they share their past noisy observations and use a Gaussian mixture model to update their local information models. This in turn helps them to obtain a better Dec-MDP policy. Simulation results show that our proposed strategy is able to predict the information model closer to the ground truth version than compared to other algorithms. Furthermore, the reduction in the overall uncertainty is more than comparable algorithms.
Award ID(s):
Publication Date:
Journal Name:
International Symposium Distributed Autonomous Robotic Systems
Sponsoring Org:
National Science Foundation
More Like this
  1. We consider a planning problem for a robot operating in an information-degraded environment. Our contribution to the state of the art is addressing this problem when robots have limited sensing capabilities, and thus only acquire information in certain locations. We therefore need a method that balances between driving the robot to the goal and toward regions to gain information (or to reduce uncertainty). We present a novel sampling-based planner (Particle Filter based Affine Quadratic Tree --- PF-AQT) that explores the environment, and plans to reach a goal with minimal uncertainty. We then use the output trajectory from PF-AQT to initialize an optimization-based planner that finds a locally optimal trajectory that minimizes control effort and uncertainty. In doing so we reap the exploration benefits of sampling-based methods and exploitation benefits of optimization-based methods for dealing with uncertainty and limited sensing capabilities of the robot. We demonstrate our results using two dynamical systems: double integrator model and a non-holonomic car-like robot.
  2. Accurately tracking dynamic targets relies on robots accounting for uncertainties in their own states to share information and maintain safety. The problem becomes even more challenging when there are an unknown and time-varying number of targets in the environment. In this paper we address this problem by introducing four new distributed algorithms that allow large teams of robots to: i) run the prediction and ii) update steps of a distributed recursive Bayesian multitarget tracker, iii) determine the set of local neighbors that must exchange data, and iv) exchange data in a consistent manner. All of these algorithms account for a bounded level of localization uncertainty in the robots by leveraging our recent introduction of the convex uncertainty Voronoi (CUV) diagram, which extends the traditional Voronoi diagram to account for localization uncertainty. The CUV diagram introduces a tessellation over the environment, which we use in this work both to distribute the multi-target tracker and to make control decisions about where to search next. We examine the efficacy of our method via a series of simulations and compare them to our previous work which assumed perfect localization.
  3. Contemporary approaches to perception, planning, estimation, and control have allowed robots to operate robustly as our remote surrogates in uncertain, unstructured environments. This progress now creates an opportunity for robots to operate not only in isolation, but also with and alongside humans in our complex environments. Realizing this opportunity requires an efficient and flexible medium through which humans can communicate with collaborative robots. Natural language provides one such medium, and through significant progress in statistical methods for natural-language understanding, robots are now able to interpret a diverse array of free-form navigation, manipulation, and mobile-manipulation commands. However, most contemporary approaches require a detailed, prior spatial-semantic map of the robot’s environment that models the space of possible referents of an utterance. Consequently, these methods fail when robots are deployed in new, previously unknown, or partially-observed environments, particularly when mental models of the environment differ between the human operator and the robot. This paper provides a comprehensive description of a novel learning framework that allows field and service robots to interpret and correctly execute natural-language instructions in a priori unknown, unstructured environments. Integral to our approach is its use of language as a “sensor”—inferring spatial, topological, and semantic information implicit in natural-language utterancesmore »and then exploiting this information to learn a distribution over a latent environment model. We incorporate this distribution in a probabilistic, language grounding model and infer a distribution over a symbolic representation of the robot’s action space, consistent with the utterance. We use imitation learning to identify a belief-space policy that reasons over the environment and behavior distributions. We evaluate our framework through a variety of different navigation and mobile-manipulation experiments involving an unmanned ground vehicle, a robotic wheelchair, and a mobile manipulator, demonstrating that the algorithm can follow natural-language instructions without prior knowledge of the environment.« less
  4. Practical robot designs must strike a compromise between fabrication/manufacture cost and anticipated execution performance. Compared to parsimonious designs, more capable (and hence more expensive) robots generally achieve their ends with greater efficiency. This paper examines how the roboticist might explore the space of designs to gain an understanding of such trade-offs. We focus, specifically, on design choices that alter the set of actions available to the robot, and model those actions as involving uncertainty. We consider planning problems under the Markov Decision Process (MDP) model, which leads us to examine how to relate the cost of some design to the expected cost of an execution for the optimal policies feasible with that design. The complexity of this problem –-expressed via hardness in the fixed parameter tractability sense–- depends on the number of actions to choose from. When that number is not negligible, we give a novel representation and an algorithm utilizing that structure that allows useful savings over naive enumeration.
  5. Physical interaction between humans and robots can help robots learn to perform complex tasks. The robot arm gains information by observing how the human kinesthetically guides it throughout the task. While prior works focus on how the robot learns, it is equally important that this learning is transparent to the human teacher. Visual displays that show the robot’s uncertainty can potentially communicate this information; however, we hypothesize that visual feedback mechanisms miss out on the physical connection between the human and robot. In this work we present a soft haptic display that wraps around and conforms to the surface of a robot arm, adding a haptic signal at an existing point of contact without significantly affecting the interaction. We demonstrate how soft actuation creates a salient haptic signal while still allowing flexibility in device mounting. Using a psychophysics experiment, we show that users can accurately distinguish inflation levels of the wrapped display with an average Weber fraction of 11.4%. When we place the wrapped display around the arm of a robotic manipulator, users are able to interpret and leverage the haptic signal in sample robot learning tasks, improving identification of areas where the robot needs more training and enabling themore »user to provide better demonstrations. See videos of our device and user studies here:« less