Learning-Based Bias Correction for Time Difference of Arrival Ultra-Wideband Localization of Resource-Constrained Mobile Robots

Zhao, Wenda; Panerati, Jacopo; Schoellig, Angela P.

doi:10.1109/lra.2021.3064199

Cited by 41 publications

(24 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, visionbased DL/RL algorithms for obstacle avoidance [24], [25], [26] being computed on external computers, and nano-drones localization systems with additional ad-hoc infrastructure (e.g., ultra-wideband anchors, motion-capture cameras, etc.) [24], [27]. Offloading computational-intense workloads to remote base-stations can enable complex algorithms fed with abundant sensory data streams from the aircraft.…”

Section: Related Workmentioning

confidence: 99%

Fully Onboard AI-Powered Human-Drone Pose Estimation on Ultralow-Power Autonomous Flying Nano-UAVs

Palossi

Zimmerman

Burrello

et al. 2022

IEEE Internet Things J.

View full text Add to dashboard Cite

Many emerging applications of nano-sized unmanned aerial vehicles (UAVs), with a few cm 2 form-factor, revolve around safely interacting with humans in complex scenarios, for example, monitoring their activities or looking after people needing care. Such sophisticated autonomous functionality must be achieved while dealing with severe constraints in payload, battery, and power budget (∼100 mW). In this work, we attack a complex task going from perception to control: to estimate and maintain the nano-UAV's relative 3D pose with respect to a person while they freely move in the environment -a task that, to the best of our knowledge, has never previously been targeted with fully onboard computation on a nano-sized UAV. Our approach is centered around a novel vision-based deep neural network (DNN), called PULP-Frontnet, designed for deployment on top of a parallel ultra-low-power (PULP) processor aboard a nano-UAV. We present a vertically integrated approach starting from the DNN model design, training, and dataset augmentation down to 8-bit quantization and deployment in-field. PULP-Frontnet can operate in real-time (up to 135 frame/s), consuming less than 87 mW for processing at peak throughput and down to 0.43 mJ/frame in the most energy-efficient operating point. Field experiments demonstrate a closed-loop top-notch autonomous navigation capability, with a tiny 27-grams Crazyflie 2.1 nano-UAV. Compared against an ideal sensing setup, onboard pose inference yields excellent drone behavior in terms of median absolute errors, such as positional (onboard: 41 cm, ideal: 26 cm) and angular (onboard: 3.7 • , ideal: 4.1 • ). We publicly release videos and the source code of our work.

show abstract

Section: Related Workmentioning

confidence: 99%

Fully Onboard AI-Powered Human-Drone Pose Estimation on Ultralow-Power Autonomous Flying Nano-UAVs

Palossi

Zimmerman

Burrello

et al. 2022

IEEE Internet Things J.

View full text Add to dashboard Cite

show abstract

“…Other strategies bet on the fusion of UWB data with those coming from INS [ 24 ], and Optitrack [ 25 ]. Additionally, it has been tried to improve UWB systems’ results on a platform of mobile robots using Gaussian processes [ 26 ] and neural networks [ 27 ].…”

Section: Background and Related Workmentioning

confidence: 99%

Sensor Information Sharing Using a Producer-Consumer Algorithm on Small Vehicles

Vazquez-Lopez

Lozada

Sandoval-Gutierrez

et al. 2021

Sensors

View full text Add to dashboard Cite

There are several tools, frameworks, and algorithms to solve information sharing from multiple tasks and robots. Some applications such as ROS, Kafka, and MAVLink cover most problems when using operating systems. However, they cannot be used for particular problems that demand optimization of resources. Therefore, the objective was to design a solution to fit the resources of small vehicles. The methodology consisted of defining the group of vehicles with low performance or are not compatible with high-level known applications; design a reduced, modular, and compatible architecture; design a producer-consumer algorithm that adjusts to the simultaneous localization and communication of multiple vehicles with UWB sensors; validate the operation with an interception task. The results showed the feasibility of performing architecture for embedded systems compatible with other applications managing information through the proposed algorithm allowed to complete the interception task between two vehicles. Another result was to determine the system’s efficiency by scaling the memory size and comparing its performance. The work’s contributions show the areas of opportunity to develop architectures focusing on the optimization of robot resources and complement existing ones.

show abstract

“…As a result, energy detection (ED)-based ToA estimation which is simple and requires a sampling rate much less than the Nyquist rate has attracted a lot of interest [27], [28], [31]- [34]. On the contrary, positioning methods based on machine learning [6], [16], [35]- [38] or deep learning [39], [40] are computationally complex and impose delay in position updates [41]. Furthermore, these methods are challenging to train and depend on the trained environment [41].…”

Section: Introductionmentioning

confidence: 99%

A Superior Iterative Transmitted-Reference Pulse Cluster Ultra-Wideband System for Ranging and Communication

Khani¹

2022

Preprint

View full text Add to dashboard Cite

Ultra-wideband (UWB) signals penetrate obstacles, achieve centimeter-level ranging accuracy, and provide low-SNR communication. These features make UWB technology a good candidate for applications demanding accurate ranging and low-power communication. Iterative transmitted-reference pulse cluster (ITRPC) UWB system increases the data rate, the power efficiency, and the accuracy of the time-of-arrival (ToA) estimation compared to the conventional<br>transmitted-reference pulse cluster system. Among the ranging techniques, ToA or its simpler version time-difference-of-arrival scheme can perfectly exploit the ultra-wide bandwidth of UWB signals to attain centimeter-level ranging accuracy. Hence, this paper considers ToA estimation for ranging. This paper proposes a novel ITRPC system that significantly outperforms the existing one. Simulation results show that the proposed analog ITRPC receiver improves the ToA estimation by about 6 dB and enhances the symbol detection by about 1:5 dB. Moreover,<br>an accurate analysis is developed to calculate the bit-error probability of the proposed ITRPC receiver in the presence of noise and monobit quantization. To the best of our knowledge, accurate analysis of a data-aided pilot recovery system has not yet been reported in the literature. The<br>paper also covers some points for implementing and theoretical analysis of the proposed system.

show abstract

Learning-Based Bias Correction for Time Difference of Arrival Ultra-Wideband Localization of Resource-Constrained Mobile Robots

Cited by 41 publications

References 27 publications

Fully Onboard AI-Powered Human-Drone Pose Estimation on Ultralow-Power Autonomous Flying Nano-UAVs

Fully Onboard AI-Powered Human-Drone Pose Estimation on Ultralow-Power Autonomous Flying Nano-UAVs

Sensor Information Sharing Using a Producer-Consumer Algorithm on Small Vehicles

A Superior Iterative Transmitted-Reference Pulse Cluster Ultra-Wideband System for Ranging and Communication

Contact Info

Product

Resources

About