arXiv subjects

Joshua Smith

Publications and source records attributed to Joshua Smith.

At least 19 recordsLinked to original sources

arXiv2025

Radiolunadiff: Estimation of wireless network signal strength in lunar terrain

In this paper, we propose a novel physics-informed deep learning architecture for predicting radio maps over lunar terrain. Our approach integrates a physics-based lunar terrain generator, which produces realistic topography informed by publicly available NASA data, with a ray-tracing engine to create a high-fidelity dataset of radio propagation scenarios. Building on this dataset, we introduce a triplet-UNet architecture, consisting of two standard UNets and a diffusion network, to model complex propagation effects. Experimental results demonstrate that our method outperforms existing deep learning approaches on our terrain dataset across various metrics.

eess.SP↗

arXiv2025

TetraGrip: Sensor-Driven Multi-Suction Reactive Object Manipulation in Cluttered Scenes

Warehouse robotic systems equipped with vacuum grippers must reliably grasp a diverse range of objects from densely packed shelves. However, these environments present significant challenges, including occlusions, diverse object orientations, stacked and obstructed items, and surfaces that are difficult to suction. We introduce \tetra, a novel vacuum-based grasping strategy featuring four suction cups mounted on linear actuators. Each actuator is equipped with an optical time-of-flight (ToF) proximity sensor, enabling reactive grasping. We evaluate \tetra in a warehouse-style setting, demonstrating its ability to manipulate objects in stacked and obstructed configurations. Our results show that our RL-based policy improves picking success in stacked-object scenarios by 22.86\% compared to a single-suction gripper. Additionally, we demonstrate that TetraGrip can successfully grasp objects in scenarios where a single-suction gripper fails due to physical limitations, specifically in two cases: (1) picking an object occluded by another object and (2) retrieving an object in a complex scenario. These findings highlight the advantages of multi-actuated, suction-based grasping in unstructured warehouse environments. The project website is available at: \href{https://tetragrip.github.io/}{https://tetragrip.github.io/}.

cs.RO↗

arXiv2024

OptiGrasp: Optimized Grasp Pose Detection Using RGB Images for Warehouse Picking Robots

In warehouse environments, robots require robust picking capabilities to manage a wide variety of objects. Effective deployment demands minimal hardware, strong generalization to new products, and resilience in diverse settings. Current methods often rely on depth sensors for structural information, which suffer from high costs, complex setups, and technical limitations. Inspired by recent advancements in computer vision, we propose an innovative approach that leverages foundation models to enhance suction grasping using only RGB images. Trained solely on a synthetic dataset, our method generalizes its grasp prediction capabilities to real-world robots and a diverse range of novel objects not included in the training set. Our network achieves an 82.3\% success rate in real-world applications. The project website with code and data will be available at http://optigrasp.github.io.

cs.RO↗

arXiv2023

Gravity Spy: Lessons Learned and a Path Forward

The Gravity Spy project aims to uncover the origins of glitches, transient bursts of noise that hamper analysis of gravitational-wave data. By using both the work of citizen-science volunteers and machine-learning algorithms, the Gravity Spy project enables reliable classification of glitches. Citizen science and machine learning are intrinsically coupled within the Gravity Spy framework, with machine-learning classifications providing a rapid first-pass classification of the dataset and enabling tiered volunteer training, and volunteer-based classifications verifying the machine classifications, bolstering the machine-learning training set and identifying new morphological classes of glitches. These classifications are now routinely used in studies characterizing the performance of the LIGO gravitational-wave detectors. Providing the volunteers with a training framework that teaches them to classify a wide range of glitches, as well as additional tools to aid their investigations of interesting glitches, empowers them to make discoveries of new classes of glitches. This demonstrates that, when giving suitable support, volunteers can go beyond simple classification tasks to identify new features in data at a level comparable to domain experts. The Gravity Spy project is now providing volunteers with more complicated data that includes auxiliary monitors of the detector to identify the root cause of glitches.

gr-qc↗

arXiv2023

Characterizing Gravitational Wave Detector Networks: From A$^\sharp$ to Cosmic Explorer

Gravitational-wave observations by the Laser Interferometer Gravitational-Wave Observatory (LIGO) and Virgo have provided us a new tool to explore the Universe on all scales from nuclear physics to the cosmos and have the massive potential to further impact fundamental physics, astrophysics, and cosmology for decades to come. In this paper we have studied the science capabilities of a network of LIGO detectors when they reach their best possible sensitivity, called A#, given the infrastructure in which they exist and a new generation of observatories that are factor of 10 to 100 times more sensitive (depending on the frequency), in particular a pair of L-shaped Cosmic Explorer observatories (one 40 km and one 20 km arm length) in the US and the triangular Einstein Telescope with 10 km arms in Europe. The presence of one or two A# observatories in a network containing two or one next generation observatories, respectively, will provide good localization capabilities for facilitating multimessenger astronomy and precision measurement of the Hubble parameter. Two Cosmic Explorer observatories are indispensable for achieving precise localization of binary neutron star events, facilitating detection of electromagnetic counterparts and transforming multimessenger astronomy. Their combined operation is even more important in the detection and localization of high-redshift sources, such as binary neutron stars, beyond the star-formation peak, and primordial black hole mergers, which may occur roughly 100 million years after the Big Bang. The addition of the Einstein Telescope to a network of two Cosmic Explorer observatories is critical for accomplishing all the identified science metrics. For most metrics the triple network of next generation terrestrial observatories are a factor 100 better than what can be accomplished by a network of three A# observatories.

gr-qc↗

arXiv2023

Cosmic Explorer: A Submission to the NSF MPSAC ngGW Subcommittee

Gravitational-wave astronomy has revolutionized humanity's view of the universe, a revolution driven by observations that no other field can make. This white paper describes an observatory that builds on decades of investment by the National Science Foundation and that will drive discovery for decades to come: Cosmic Explorer. Major discoveries in astronomy are driven by three related improvements: better sensitivity, higher precision, and opening new observational windows. Cosmic Explorer promises all three and will deliver an order-of-magnitude greater sensitivity than LIGO. Cosmic Explorer will push the gravitational-wave frontier to almost the edge of the observable universe using technologies that have been proven by LIGO during its development. With the unprecedented sensitivity that only a new facility can deliver, Cosmic Explorer will make discoveries that cannot yet be anticipated, especially since gravitational waves are both synergistic with electromagnetic observations and can reach into regions of the universe that electromagnetic observations cannot explore. With Cosmic Explorer, scientists can use the universe as a laboratory to test the laws of physics and study the nature of matter. Cosmic Explorer allows the United States to continue its leading role in gravitational-wave science and the international network of next-generation observatories. With its extraordinary discovery potential, Cosmic Explorer will deliver revolutionary observations across astronomy, physics, and cosmology including: Black Holes and Neutron Stars Throughout Cosmic Time, Multi-Messenger Astrophysics and Dynamics of Dense Matter, New Probes of Extreme Astrophysics, Fundamental Physics and Precision Cosmology, Dark Matter and the Early Universe.

astro-ph.IM↗

arXiv2023

The most luminous, merger-free AGN show only marginal correlation with bar presence

The role of large-scale bars in the fuelling of active galactic nuclei (AGN) is still debated, even as evidence mounts that black hole growth in the absence of galaxy mergers cumulatively dominated and may substantially influence disc (i.e., merger-free) galaxy evolution. We investigate whether large-scale galactic bars are a good candidate for merger-free AGN fuelling. Specifically, we combine slit spectroscopy and Hubble Space Telescope imagery to characterise star formation rates (SFRs) and stellar masses of the unambiguously disc-dominated host galaxies of a sample of luminous, Type-1 AGN with 0.02 < z 0.024. After carefully correcting for AGN signal, we find no clear difference in SFR between AGN hosts and a stellar mass-matched sample of galaxies lacking an AGN (0.013 < z < 0.19), although this could be due to a small sample size (n_AGN = 34). We correct for SFR and stellar mass to minimise selection biases, and compare the bar fraction in the two samples. We find that AGN are marginally (1.7$\sigma$) more likely to host a bar than inactive galaxies, with AGN hosts having a bar fraction, fbar = 0.59^{+0.08}_{-0.09} and inactive galaxies having a bar fraction fbar = 0.44^{+0.08}_{-0.09}. However, we find no further differences between SFR- and mass-matched AGN and inactive samples. While bars could potentially trigger AGN activity, they appear to have no further, unique effect on a galaxy's stellar mass or SFR.

astro-ph.GA↗

arXiv2022

Hierarchical Control Strategy for Moving A Robot Manipulator Between Small Containers

In this paper, we study the implementation of a model predictive controller (MPC) for the task of object manipulation in a highly uncertain environment (e.g., picking objects from a semi-flexible array of densely packed bins). As a real-time perception-driven feedback controller, MPC is robust to the uncertainties in this environment. However, our experiment shows MPC cannot control a robot to complete a sequence of motions in a heavily occluded environment due to its myopic nature. It will benefit from adding a high-level policy that adaptively adjusts the optimization problem for MPC.

cs.RO↗

arXiv2022

NeuriCam: Key-Frame Video Super-Resolution and Colorization for IoT Cameras

We present NeuriCam, a novel deep learning-based system to achieve video capture from low-power dual-mode IoT camera systems. Our idea is to design a dual-mode camera system where the first mode is low-power (1.1 mW) but only outputs grey-scale, low resolution, and noisy video and the second mode consumes much higher power (100 mW) but outputs color and higher resolution images. To reduce total energy consumption, we heavily duty cycle the high power mode to output an image only once every second. The data for this camera system is then wirelessly sent to a nearby plugged-in gateway, where we run our real-time neural network decoder to reconstruct a higher-resolution color video. To achieve this, we introduce an attention feature filter mechanism that assigns different weights to different features, based on the correlation between the feature map and the contents of the input frame at each spatial location. We design a wireless hardware prototype using off-the-shelf cameras and address practical issues including packet loss and perspective mismatch. Our evaluations show that our dual-camera approach reduces energy consumption by 7x compared to existing systems. Further, our model achieves an average greyscale PSNR gain of 3.7 dB over prior single and dual-camera video super-resolution methods and 5.6 dB RGB gain over prior color propagation methods. Open-source code: https://github.com/vb000/NeuriCam.

cs.CV↗

arXiv2022

Electrostatic Brakes Enable Individual Joint Control of Underactuated, Highly Articulated Robots

Highly articulated organisms serve as blueprints for incredibly dexterous mechanisms, but building similarly capable robotic counterparts has been hindered by the difficulties of developing electromechanical actuators with both the high strength and compactness of biological muscle. We develop a stackable electrostatic brake that has comparable specific tension and weight to that of muscles and integrate it into a robotic joint. Compared to electromechanical motors, our brake-equipped joint is four times lighter and one thousand times more power efficient while exerting similar holding torques. Our joint design enables a ten degree-of-freedom robot equipped with only one motor to manipulate multiple objects simultaneously. We also show that the use of brakes allows a two-fingered robot to perform in-hand re-positioning of an object 45% more quickly and with 53% lower positioning error than without brakes. Relative to fully actuated robots, our findings suggest that robots equipped with such electrostatic brakes will have lower weight, volume, and power consumption yet retain the ability to reach arbitrary joint configurations.

cs.RO↗

arXiv2021

3G R&D: R&D for the Next Generation of Ground-based Gravitational-wave Detectors

To deliver on the promise of next generation gravitational-wave observatories, a sustained and coordinated detector research and development program is required. This report examines in detail the wide range of nearer- and longer-term detector R&D programs needed for next generation GW detectors commensurate with the key science targets presented in "The Next Generation Global Gravitational Wave Observatory: The Science Book", including considerations of site selection and large-scale vacuum infrastructure. The report makes a series of detailed recommendations on the needed advances in detector technology and the timescales needed to achieve those advances. It also identifies areas where larger-scale globally coordinated R&D efforts will be critical to ensuring success while minimizing costs. This report is the third in a six part series of reports by the GWIC 3G Subcommittee: i) Expanding the Reach of Gravitational Wave Observatories to the Edge of the Universe, ii) The Next Generation Global Gravitational Wave Observatory: The Science Book, iii) 3G R&D: R&D for the Next Generation of Ground-based Gravitational Wave Detectors (this report), iv) Gravitational Wave Data Analysis: Computing Challenges in the 3G Era, v) Future Ground-based Gravitational-wave Observatories: Synergies with Other Scientific Communities, and vi) An Exploration of Possible Governance Models for the Future Global Gravitational-Wave Observatory Network.

gr-qc↗

arXiv2020

Iterative Semi-parametric Dynamics Model Learning For Autonomous Racing

Accurately modeling robot dynamics is crucial to safe and efficient motion control. In this paper, we develop and apply an iterative learning semi-parametric model, with a neural network, to the task of autonomous racing with a Model Predictive Controller (MPC). We present a novel non-linear semi-parametric dynamics model where we represent the known dynamics with a parametric model, and a neural network captures the unknown dynamics. We show that our model can learn more accurately than a purely parametric model and generalize better than a purely non-parametric model, making it ideal for real-world applications where collecting data from the full state space is not feasible. We present a system where the model is bootstrapped on pre-recorded data and then updated iteratively at run time. Then we apply our iterative learning approach to the simulated problem of autonomous racing and show that it can safely adapt to modified dynamics online and even achieve better performance than models trained on data from manual driving.

cs.RO↗

arXiv2020

Advances and Open Problems in Backscatter Networking

Despite significant research in backscatter communication over the past decade, key technical open problems remain under-explored. Here, we first systematically lay out the design space for backscatter networking and identify applications that make backscatter an attractive communication primitive. We then identify 10 research problems that remain to be solved in backscatter networking. These open problems span across the network stack to include circuits, embedded systems, physical layer, MAC and network protocols as well as applications. We believe that addressing these problems can help deliver on backscatter's promise of low-power ubiquitous connectivity.

cs.NI↗

arXiv2020

Online Dynamic Trajectory Optimization and Control for a Quadruped Robot

Legged robot locomotion requires the planning of stable reference trajectories, especially while traversing uneven terrain. The proposed trajectory optimization framework is capable of generating dynamically stable base and footstep trajectories for multiple steps. The locomotion task can be defined with contact locations, base motion or both, making the algorithm suitable for multiple scenarios (e.g., presence of moving obstacles). The planner uses a simplified momentum-based task space model for the robot dynamics, allowing computation times that are fast enough for online replanning.This fast planning capabilitiy also enables the quadruped to accommodate for drift and environmental changes. The algorithm is tested on simulation and a real robot across multiple scenarios, which includes uneven terrain, stairs and moving obstacles. The results show that the planner is capable of generating stable trajectories in the real robot even when a box of 15 cm height is placed in front of its path at the last moment.

cs.RO↗

arXiv2020

Variable Autonomy of Whole-body Control for Inspection and Intervention in Industrial Environments using Legged Robots

The deployment of robots in industrial and civil scenarios is a viable solution to protect operators from danger and hazards. Shared autonomy is paramount to enable remote control of complex systems such as legged robots, allowing the operator to focus on the essential tasks instead of overly detailed execution. To realize this, we propose a comprehensive control framework for inspection and intervention using a legged robot and validate the integration of multiple loco-manipulation algorithms optimised for improving the remote operation. The proposed control offers 3 operation modes: fully automated, semi-autonomous, and the haptic interface receiving onsite physical interaction for assisting teleoperation. Our contribution is the design of a QP-based semi-analytical whole-body control, which is the key to the various task completion subject to internal and external constraints. We demonstrate the versatility of the whole-body control in terms of decoupling tasks, singularity tolerance and constraint satisfaction. We deploy our solution in field trials and evaluate in an emergency setting by an E-stop while the robot is clearing road barriers and traversing difficult terrains.

cs.RO↗

arXiv2020

Adversarial Generation of Informative Trajectories for Dynamics System Identification

Dynamic System Identification approaches usually heavily rely on the evolutionary and gradient-based optimisation techniques to produce optimal excitation trajectories for determining the physical parameters of robot platforms. Current optimisation techniques tend to generate single trajectories. This is expensive, and intractable for longer trajectories, thus limiting their efficacy for system identification. We propose to tackle this issue by using multiple shorter cyclic trajectories, which can be generated in parallel, and subsequently combined together to achieve the same effect as a longer trajectory. Crucially, we show how to scale this approach even further by increasing the generation speed and quality of the dataset through the use of generative adversarial network (GAN) based architectures to produce a large databases of valid and diverse excitation trajectories. To the best of our knowledge, this is the first robotics work to explore system identification with multiple cyclic trajectories and to develop GAN-based techniques for scaleably producing excitation trajectories that are diverse in both control parameter and inertial parameter spaces. We show that our approach dramatically accelerates trajectory optimisation, while simultaneously providing more accurate system identification than the conventional approach.

cs.RO↗

arXiv2020

A Cryogenic Silicon Interferometer for Gravitational-wave Detection

The detection of gravitational waves from compact binary mergers by LIGO has opened the era of gravitational wave astronomy, revealing a previously hidden side of the cosmos. To maximize the reach of the existing LIGO observatory facilities, we have designed a new instrument that will have 5 times the range of Advanced LIGO, or greater than 100 times the event rate. Observations with this new instrument will make possible dramatic steps toward understanding the physics of the nearby universe, as well as observing the universe out to cosmological distances by the detection of binary black hole coalescences. This article presents the instrument design and a quantitative analysis of the anticipated noise floor.

astro-ph.IM↗

arXiv2019

Bounded haptic teleoperation of a quadruped robot's foot posture for sensing and manipulation

This paper presents a control framework to teleoperate a quadruped robot's foot for operator-guided haptic exploration of the environment. Since one leg of a quadruped robot typically only has 3 actuated degrees of freedom (DoFs), the torso is employed to assist foot posture control via a hierarchical whole-body controller. The foot and torso postures are controlled by two analytical Cartesian impedance controllers cascaded by a null space projector. The contact forces acting on supporting feet are optimized by quadratic programming (QP). The foot's Cartesian impedance controller may also estimate contact forces from trajectory tracking errors, and relay the force-feedback to the operator. A 7D haptic joystick, Sigma.7, transmits motion commands to the quadruped robot ANYmal, and renders the force feedback. Furthermore, the joystick's motion is bounded by mapping the foot's feasible force polytope constrained by the friction cones and torque limits in order to prevent the operator from driving the robot to slipping or falling over. Experimental results demonstrate the efficiency of the proposed framework.

cs.RO↗