POMDP-lite for robust robot planning under uncertainty

Chen, Min; Hsu, David; Lee, Wee Sun

doi:10.1109/icra.2016.7487754

Cited by 50 publications

(41 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Firstly, analysis from Chen et al [4], where the authors show that under mild assumptions POMDPs can be reduced to sequence of MDPs, is promising for obtaining better regret guarantees.…”

Section: Discussionmentioning

confidence: 99%

“…Hence, the realizability error of the policy is due to two terms -firstly the information mismatch and secondly the expressiveness of feature space. This realizability error can be 4 Imitation of a clairvoyant oracle in information gathering has been explored by Choudhury et al [7]. We subsume the presented algorithm, EXPLORE, in our framework (as Algorithm QVALAGG) and instead focus on the theoretical insight on what it means to imitate a clairvoyant oracle.…”

Section: Analysis Using a Hallucinating Oraclementioning

confidence: 99%

“…In this work we define cumulative reward gathered by a clairvoyant oracle as the value function to imitate 4 . This has been shown to be effective by Kahn et al [20], Sun et al [39], Karkus et al [21].…”

Section: Solving Pomdp Via Imitation Of a Clairvoyant Oraclementioning

confidence: 99%

See 2 more Smart Citations

Adaptive Information Gathering via Imitation Learning

Choudhury

Kapoor

Ranade

et al. 2017

Robotics: Science and Systems XIII

View full text Add to dashboard Cite

Abstract-In the adaptive information gathering problem, a policy is required to select an informative sensing location using the history of measurements acquired thus far. While there is an extensive amount of prior work investigating effective practical approximations using variants of Shannon's entropy, the efficacy of such policies heavily depends on the geometric distribution of objects in the world. On the other hand, the principled approach of employing online POMDP solvers is rendered impractical by the need to explicitly sample online from a posterior distribution of world maps.We present a novel data-driven imitation learning framework to efficiently train information gathering policies. The policy imitates a clairvoyant oracle -an oracle that at train time has full knowledge about the world map and can compute maximally informative sensing locations. We analyze the learnt policy by showing that offline imitation of a clairvoyant oracle is implicitly equivalent to online oracle execution in conjunction with posterior sampling. This observation allows us to obtain powerful near-optimality guarantees for information gathering problems possessing an adaptive sub-modularity property. As demonstrated on a spectrum of 2D and 3D exploration problems, the trained policies enjoy the best of both worlds -they adapt to different world map distributions while being computationally inexpensive to evaluate.

show abstract

“…Firstly, analysis from Chen et al [4], where the authors show that under mild assumptions POMDPs can be reduced to sequence of MDPs, is promising for obtaining better regret guarantees.…”

Section: Discussionmentioning

confidence: 99%

Section: Analysis Using a Hallucinating Oraclementioning

confidence: 99%

See 1 more Smart Citation

Adaptive Information Gathering via Imitation Learning

Choudhury

Kapoor

Ranade

et al. 2017

Robotics: Science and Systems XIII

View full text Add to dashboard Cite

show abstract

“…In its most general form, the data gathering task amounts to one of sequential decision-making under uncertainty, which can be expressed as a partially observable Markov decision process (POMDP) (Kaelbling et al 1998). Unfortunately, despite substantial progress in recent years (Chen et al 2016;Kurniawati et al 2008), solving large-scale POMDP models remains an open challenge, motivating more efficient solutions.…”

Section: Informative Planningmentioning

confidence: 99%

An informative path planning framework for UAV-based terrain monitoring

Popović

Vidal-Calleja

Hitz³

et al. 2020

Auton Robot

132

103

View full text Add to dashboard Cite

Unmanned aerial vehicles represent a new frontier in a wide range of monitoring and research applications. To fully leverage their potential, a key challenge is planning missions for efficient data acquisition in complex environments. To address this issue, this article introduces a general informative path planning framework for monitoring scenarios using an aerial robot, focusing on problems in which the value of sensor information is unevenly distributed in a target area and unknown a priori. The approach is capable of learning and focusing on regions of interest via adaptation to map either discrete or continuous variables on the terrain using variable-resolution data received from probabilistic sensors. During a mission, the terrain maps built online are used to plan information-rich trajectories in continuous 3-D space by optimizing initial solutions obtained by a coarse grid search. Extensive simulations show that our approach is more efficient than existing methods. We also demonstrate its real-time application on a photorealistic mapping scenario using a publicly available dataset and a proof of concept for an agricultural monitoring task.

show abstract

“…[20][21] These algorithms have been successfully applied to a variety of robotic tasks, including navigation, 21 autonomous driving 18 and robot motion planning. 22 Another way to accomplish such reduction is to represent the state space hierarchically. [23][24] The other obstacle is that robotic systems often have the pervasive problem of perceptual aliasing.…”

Section: Introductionmentioning

confidence: 99%

A biological-inspired episodic cognitive map building framework for mobile robot navigation

Liu

Cong

Zou

et al. 2017

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

This article proposes a self-learning method of robotic experience for building episodic cognitive map using biologically inspired episodic memory. The episodic cognitive map is used for robot navigation under uncertainty. Two main challenges which include high computational complexity and perceptual aliasing are addressed. The episodic memory-driving Markov decision process is proposed to simulate the organization of episodic memory by introducing neuron activation and stimulation mechanism. Episodic memory self-learning model and algorithm are presented for building the episodic cognitive map based on episodic memory-driving Markov decision process. Uncertain information is considered to improve mapping performance. The presented method can realize robotic memory real-time storage, incremental accumulation, integration and updating. Based on the episodic cognitive map, the predicted episodic trajectory can simply be computed by activation spreading of state neurons. The experimental results for a mobile robot indicate that the method can efficiently performs learning, localization, mapping and navigation in real-life office environments.

show abstract

POMDP-lite for robust robot planning under uncertainty

Cited by 50 publications

References 21 publications

Adaptive Information Gathering via Imitation Learning

Adaptive Information Gathering via Imitation Learning

An informative path planning framework for UAV-based terrain monitoring

A biological-inspired episodic cognitive map building framework for mobile robot navigation

Contact Info

Product

Resources

About