Results 1 - 10
of
19
Multi-robot informative path planning for active sensing of environmental phenomena: A tale of two algorithms
, 2013
"... A key problem of robotic environmental sensing and monitoring is that of active sensing: How can a team of robots plan the most informative observation paths to minimize the uncertainty in modeling and predicting an environmental phenomenon? This paper presents two principled approaches to efficient ..."
Abstract
-
Cited by 15 (13 self)
- Add to MetaCart
(Show Context)
A key problem of robotic environmental sensing and monitoring is that of active sensing: How can a team of robots plan the most informative observation paths to minimize the uncertainty in modeling and predicting an environmental phenomenon? This paper presents two principled approaches to efficient information-theoretic path planning based on entropy and mutual information criteria for in situ active sensing of an important broad class of widely-occurring environmental phenomena called anisotropic fields. Our proposed algorithms are novel in addressing a trade-off between active sensing performance and time efficiency. An important practical consequence is that our algorithms can exploit the spatial correlation structure of Gaussian process-based anisotropic fields to improve time efficiency while preserving near-optimal active sensing performance. We analyze the time complexity of our algorithms and prove analytically that they scale better than state-of-the-art algorithms with increasing planning horizon length. We provide theoretical guarantees on the active sensing performance of our algorithms for a class of exploration tasks called transect sampling, which, in particular, can be improved with longer planning time and/or lower spatial correlation along the transect. Empirical evaluation on real-world anisotropic field data shows that our algorithms can perform better or at least as well as the state-of-the-art algorithms while often incurring a few orders of magnitude less computational time, even when the field conditions are less favorable.
Gaussian Process-Based Decentralized Data Fusion and Active Sensing for Mobility-on-Demand System
"... Abstract—Mobility-on-demand (MoD) systems have recently emerged as a promising paradigm of one-way vehicle sharing for sustainable personal urban mobility in densely populated cities. In this paper, we enhance the capability of a MoD system by deploying robotic shared vehicles that can autonomously ..."
Abstract
-
Cited by 12 (9 self)
- Add to MetaCart
(Show Context)
Abstract—Mobility-on-demand (MoD) systems have recently emerged as a promising paradigm of one-way vehicle sharing for sustainable personal urban mobility in densely populated cities. In this paper, we enhance the capability of a MoD system by deploying robotic shared vehicles that can autonomously cruise the streets to be hailed by users. A key challenge to managing the MoD system effectively is that of real-time, fine-grained mobility demand sensing and prediction. This paper presents a novel decentralized data fusion and active sensing algorithm for realtime, fine-grained mobility demand sensing and prediction with a fleet of autonomous robotic vehicles in a MoD system. Our Gaussian process (GP)-based decentralized data fusion algorithm can achieve a fine balance between predictive power and time efficiency. We theoretically guarantee its predictive performance to be equivalent to that of a sophisticated centralized sparse approximation for the GP model: The computation of such a sparse approximate GP model can thus be distributed among the MoD vehicles, hence achieving efficient and scalable demand prediction. Though our decentralized active sensing strategy is devised to gather the most informative demand data for demand prediction, it can achieve a dual effect of fleet rebalancing to service the mobility demands. Empirical evaluation on real-world mobility demand data shows that our proposed algorithm can achieve a better balance between predictive accuracy and time efficiency than state-of-the-art algorithms. I.
Parallel Gaussian Process Regression with Low-Rank Covariance Matrix Approximations
"... Gaussian processes (GP) are Bayesian nonparametric models that are widely used for probabilistic regression. Unfortunately, it cannot scale well with large data nor perform real-time predictions due to its cubic time cost in the data size. This paper presents two parallel GP regression methods that ..."
Abstract
-
Cited by 9 (9 self)
- Add to MetaCart
(Show Context)
Gaussian processes (GP) are Bayesian nonparametric models that are widely used for probabilistic regression. Unfortunately, it cannot scale well with large data nor perform real-time predictions due to its cubic time cost in the data size. This paper presents two parallel GP regression methods that exploit low-rank covariance matrix approximations for distributing the computational load among parallel machines to achieve time efficiency and scalability. We theoretically guarantee the predictive performances of our proposed parallel GPs to be equivalent to that of some centralized approximate GP regression methods: The computation of their centralized counterparts can be distributed among parallel machines, hence achieving greater time efficiency and scalability. We analytically compare the properties of our parallel GPs such as time, space, and communication complexity. Empirical evaluation on two real-world datasets in a cluster of 20 computing nodes shows that our parallel GPs are significantly more time-efficient and scalable than their centralized counterparts and exact/full GP while achieving predictive performances comparable to full GP. 1
Hierarchical Bayesian nonparametric approach to modeling and learning the wisdom of crowds of urban traffic route planning agents
- In Proc. IAT
, 2012
"... Abstract—Route prediction is important to analyzing and understanding the route patterns and behavior of traffic crowds. Its objective is to predict the most likely or “popular” route of road segments from a given point in a road network. This paper presents a hierarchical Bayesian non-parametric ap ..."
Abstract
-
Cited by 6 (4 self)
- Add to MetaCart
(Show Context)
Abstract—Route prediction is important to analyzing and understanding the route patterns and behavior of traffic crowds. Its objective is to predict the most likely or “popular” route of road segments from a given point in a road network. This paper presents a hierarchical Bayesian non-parametric approach to efficient and scalable route prediction that can harness the wisdom of crowds of route planning agents by aggregating their sequential routes of possibly varying lengths and origin-destination pairs. In particular, our approach has the advantages of (a) not requiring a Markov assumption to be imposed and (b) generalizing well with sparse data, thus resulting in significantly improved prediction accuracy, as demonstrated empirically using real-world taxi route data. We also show two practical applications of our route prediction algorithm: predictive taxi ranking and route recommendation. Keywords-wisdom of crowds; crowdsourcing; sequential decision making; route prediction; intelligent transportation systems; hierarchical Dirichlet and Pitman-Yor process I.
A general framework for interacting Bayes-optimally with self-interested agents using arbitrary parametric model and model prior. arXiv:1304.2024
, 2013
"... Recent advances in Bayesian reinforcement learn-ing (BRL) have shown that Bayes-optimality is theoretically achievable by modeling the envi-ronment’s latent dynamics using Flat-Dirichlet-Multinomial (FDM) prior. In self-interested multi-agent environments, the transition dynamics are mainly controll ..."
Abstract
-
Cited by 5 (4 self)
- Add to MetaCart
Recent advances in Bayesian reinforcement learn-ing (BRL) have shown that Bayes-optimality is theoretically achievable by modeling the envi-ronment’s latent dynamics using Flat-Dirichlet-Multinomial (FDM) prior. In self-interested multi-agent environments, the transition dynamics are mainly controlled by the other agent’s stochastic behavior for which FDM’s independence and mod-eling assumptions do not hold. As a result, FDM does not allow the other agent’s behavior to be generalized across different states nor specified us-ing prior domain knowledge. To overcome these practical limitations of FDM, we propose a gener-alization of BRL to integrate the general class of parametric models and model priors, thus allowing practitioners ’ domain knowledge to be exploited to produce a fine-grained and compact representation of the other agent’s behavior. Empirical evalua-tion shows that our approach outperforms existing multi-agent reinforcement learning algorithms. 1
Parallel Gaussian process regression for big data: Low-rank representation meets Markov approximation. arXiv:1411.4510
"... The expressive power of a Gaussian process (GP) model comes at a cost of poor scalability in the data size. To improve its scalability, this paper presents a low-rank-cum-Markov approximation (LMA) of the GP model that is novel in leveraging the dual computational advantages stemming from complement ..."
Abstract
-
Cited by 5 (5 self)
- Add to MetaCart
(Show Context)
The expressive power of a Gaussian process (GP) model comes at a cost of poor scalability in the data size. To improve its scalability, this paper presents a low-rank-cum-Markov approximation (LMA) of the GP model that is novel in leveraging the dual computational advantages stemming from complementing a low-rank approximate representation of the full-rank GP based on a support set of inputs with a Markov approximation of the resulting residual process; the latter approximation is guaranteed to be closest in the Kullback-Leibler dis-tance criterion subject to some constraint and is consid-erably more refined than that of existing sparse GP mod-els utilizing low-rank representations due to its more re-laxed conditional independence assumption (especially with larger data). As a result, our LMA method can trade off between the size of the support set and the or-der of the Markov property to (a) incur lower computa-tional cost than such sparse GP models while achieving predictive performance comparable to them and (b) ac-curately represent features/patterns of any scale. Inter-estingly, varying the Markov order produces a spectrum of LMAs with PIC approximation and full-rank GP at the two extremes. An advantage of our LMA method is that it is amenable to parallelization on multiple ma-chines/cores, thereby gaining greater scalability. Empir-ical evaluation on three real-world datasets in clusters of up to 32 computing nodes shows that our central-ized and parallel LMA methods are significantly more time-efficient and scalable than state-of-the-art sparse and full-rank GP regression methods while achieving comparable predictive performances. 1
Recent Advances in Scaling up Gaussian Process Predictive Models for Large Spatiotemporal Data
"... Abstract. The expressive power of Gaussian process (GP) models comes at a cost of poor scalability in the size of the data. To improve their scalability, this paper presents an overview of our recent progress in scaling up GP models for large spatiotemporally correlated data through parallelization ..."
Abstract
-
Cited by 4 (4 self)
- Add to MetaCart
(Show Context)
Abstract. The expressive power of Gaussian process (GP) models comes at a cost of poor scalability in the size of the data. To improve their scalability, this paper presents an overview of our recent progress in scaling up GP models for large spatiotemporally correlated data through parallelization on clusters of ma-chines, online learning, and nonmyopic active sensing/learning. 1
GP-Localize: Persistent mobile robot localization using online sparse Gaussian process observation model
- In Proc. AAAI
, 2014
"... Central to robot exploration and mapping is the task of persistent localization in environmental fields character-ized by spatially correlated measurements. This paper presents a Gaussian process localization (GP-Localize) algorithm that, in contrast to existing works, can exploit the spatially corr ..."
Abstract
-
Cited by 4 (3 self)
- Add to MetaCart
(Show Context)
Central to robot exploration and mapping is the task of persistent localization in environmental fields character-ized by spatially correlated measurements. This paper presents a Gaussian process localization (GP-Localize) algorithm that, in contrast to existing works, can exploit the spatially correlated field measurements taken during a robot’s exploration (instead of relying on prior train-ing data) for efficiently and scalably learning the GP observation model online through our proposed novel online sparse GP. As a result, GP-Localize is capable of achieving constant time and memory (i.e., independent of the size of the data) per filtering step, which demon-strates the practical feasibility of using GPs for persis-tent robot localization and autonomy. Empirical evalua-tion via simulated experiments with real-world datasets and a real robot experiment shows that GP-Localize out-performs existing GP localization algorithms. 1
Gaussian process decentralized data fusion and active sensing for spatiotemporal traffic modeling and prediction in mobilityon-demand systems
- IEEE Transactions on Automation Science and Engineering
, 2015
"... Abstract—Mobility-on-demand (MoD) systems have recently emerged as a promising paradigm of one-way vehicle sharing for sustainable personal urban mobility in densely populated cities. We assume the capability of a MoD system to be enhanced by deploying robotic shared vehicles that can autonomously c ..."
Abstract
-
Cited by 3 (3 self)
- Add to MetaCart
Abstract—Mobility-on-demand (MoD) systems have recently emerged as a promising paradigm of one-way vehicle sharing for sustainable personal urban mobility in densely populated cities. We assume the capability of a MoD system to be enhanced by deploying robotic shared vehicles that can autonomously cruise the streets to be hailed by users. A key challenge of the MoD system is that of real-time, fine-grained mobility demand and traffic flow sensing and prediction. This paper presents novel Gaussian process (GP) decentralized data fusion and active sensing algorithms for real-time, fine-grained traffic modeling and prediction with a fleet of MoD vehicles. The predictive performance of our decentralized data fusion algorithms are theoretically guaranteed to be equivalent to that of sophisticated centralized sparse GP approximations. We derive consensus filtering variants requiring only local
Spatiotemporal aquatic field reconstruction using robotic sensor swarm
, 2012
"... Monitoring important aquatic processes like harmful algal blooms is of increasing interest to public health, ecosystem sustainability, marine biology, and aquaculture industry. This article presents a novel approach to spatiotemporal aquatic field reconstruction using inexpensive, low-power mobile s ..."
Abstract
-
Cited by 2 (0 self)
- Add to MetaCart
(Show Context)
Monitoring important aquatic processes like harmful algal blooms is of increasing interest to public health, ecosystem sustainability, marine biology, and aquaculture industry. This article presents a novel approach to spatiotemporal aquatic field reconstruction using inexpensive, low-power mobile sensing platforms called robotic fish. Robotic fish networks are a typical example of cyber-physical systems where the design of cyber components (sensing, communication, and information processing) must account for inherent physical dynamics of the robots and the aquatic environment. Our approach features a rendezvous-based mobility control scheme where robotic fish collaborate in the form of a swarm to sense the aquatic environment in a series of carefully chosen rendezvous regions. We design a novel feedback control algorithm that maintains the desirable level of wireless connectivity for a sensor swarm in the presence of significant environment and system dynamics. Information-theoretic analysis is used to guide the selection of rendezvous regions so that the spatiotemporal field reconstruction accuracy is maximized subject to the limited sensor mobility. The effectiveness of our approach is validated via implementation on sensor hardware and extensive simulations based on real data traces of water surface temperature field and on-water ZigBee wireless communication.
