A survey of methods for mobile robot localization and mapping in dynamic indoor environments

Panchpor, Aishwarya A.; Shue, Sam; Conrad, James M.

doi:10.1109/spaces.2018.8316333

Cited by 47 publications

(30 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Here, we focus only on rangebased methods. We refer to [47] for a comprehensive survey on various indoor localization techniques. This category of solutions computes distances based on how long sound takes to propagate between a sender and a receiver [20, 24, 25, 28-30, 32, 38-41].…”

Section: Related Workmentioning

confidence: 99%

Rebooting Ultrasonic Positioning Systems for Ultrasound-incapable Smart Devices

Lin

Yang

2019

The 25th Annual International Conference on Mobile Computing and Networking

View full text Add to dashboard Cite

An ultrasonic Positioning System (UPS) has outperformed RF-based systems in terms of its accuracy for years. However, few of the developed solutions have been deployed in practice to satisfy the localization demand of today's smart devices, which lack ultrasonic sensors and were considered as being "deaf" to ultrasound. A recent finding demonstrates that ultrasound may be audible to the smart devices under certain conditions due to their microphone's nonlinearity. Inspired by this insight, this work revisits the ultrasonic positioning technique and builds a practical UPS, called UPS+, for ultrasound-incapable smart devices. The core concept is to deploy two types of indoor beacon devices, which will advertise ultrasonic beacons at two different ultrasonic frequencies respectively. Their superimposed beacons are shifted to a low-frequency by virtue of the nonlinearity effect at the receiver's microphone. This underlying property functions as an implicit ultrasonic downconverter without throwing harm to the hearing system of humans. We demonstrate UPS+, a fully functional UPS prototype, with centimeter-level localization accuracy using custom-made beacon hardware and well-designed algorithms.

show abstract

Section: Related Workmentioning

confidence: 99%

Rebooting Ultrasonic Positioning Systems for Ultrasound-incapable Smart Devices

Lin

Yang

2019

The 25th Annual International Conference on Mobile Computing and Networking

View full text Add to dashboard Cite

show abstract

“…Autonomous navigation considers a set of factors, such as path planning, localisation, and mapping [2]. Thus, these main problems need to be addressed to perform the robot mission.…”

Section: Problem Formulationmentioning

confidence: 99%

“…According to refs. [2,3], some problems must be solved to accomplish the robot's missions autonomously: path planning, location, and motion control. Path planning ensures a feasible trajectory that connects the starting point to a goal.…”

Section: Introductionmentioning

confidence: 99%

Hybrid Methodology for Path Planning and Computational Vision Applied to Autonomous Mission: A New Approach

Coelho¹,

Pinto²,

Souza³

et al. 2019

Robotica

View full text Add to dashboard Cite

SUMMARYIn recent years, mobile robots have become increasingly frequent in daily life applications, such as cleaning, surveillance, support for the elderly and people with disabilities, as well as hazardous activities. However, a big challenge arises when the robotic system must perform a fully autonomous mission. The main problems of autonomous missions include path planning, localisation, and mapping. Thus, this research proposes a hybrid methodology for mobile robots on an autonomous mission involving an offline approach that uses the Direct-DRRT* algorithm and the artificial potential fields algorithm as the online planner. The experimental design covers three scenarios with an increasing degree of accuracy in respect of the real world. Additionally, an extensive evaluation of the proposed methodology is reported.

show abstract

“…Traditional approaches, such as A* [8], RRT [9], artificial potential fields [10], simultaneously localization and mapping (SLAM) [11], employ two steps to handle these motion control problems with unknown environments [12]: (i) Perceive and estimate the environment state; and (ii) model and optimize the control command. These approaches are often susceptible to unforeseen disturbances, any incomplete perception, biased estimate, or inaccurate model will lead to poor performances [13].…”

Section: Introductionmentioning

confidence: 99%

Robust Motion Control for UAV in Dynamic Uncertain Environments Using Deep Reinforcement Learning

Wan

Gao

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

In this paper, a novel deep reinforcement learning (DRL) method, and robust deep deterministic policy gradient (Robust-DDPG), is proposed for developing a controller that allows robust flying of an unmanned aerial vehicle (UAV) in dynamic uncertain environments. This technique is applicable in many fields, such as penetration and remote surveillance. The learning-based controller is constructed with an actor-critic framework, and can perform a dual-channel continuous control (roll and speed) of the UAV. To overcome the fragility and volatility of original DDPG, three critical learning tricks are introduced in Robust-DDPG: (1) Delayed-learning trick, providing stable learnings, while facing dynamic environments; (2) adversarial attack trick, improving policy’s adaptability to uncertain environments; (3) mixed exploration trick, enabling faster convergence of the model. The training experiments show great improvement in its convergence speed, convergence effect, and stability. The exploiting experiments demonstrate high efficiency in providing the UAV a shorter and smoother path. While, the generalization experiments verify its better adaptability to complicated, dynamic and uncertain environments, comparing to Deep Q Network (DQN) and DDPG algorithms.

show abstract

A survey of methods for mobile robot localization and mapping in dynamic indoor environments

Cited by 47 publications

References 26 publications

Rebooting Ultrasonic Positioning Systems for Ultrasound-incapable Smart Devices

Rebooting Ultrasonic Positioning Systems for Ultrasound-incapable Smart Devices

Hybrid Methodology for Path Planning and Computational Vision Applied to Autonomous Mission: A New Approach

Robust Motion Control for UAV in Dynamic Uncertain Environments Using Deep Reinforcement Learning

Contact Info

Product

Resources

About