3D Gaussian Splatting is crucial for real-time novel view synthesis due to its efficiency and ability to render photorealistic images. However, building a 3D Gaussian is guided solely by photometric loss, which can result in inconsistencies in reconstruction. This under-constrained process often results in "floater" artifacts and unstructured geometry, preventing the extraction of high-fidelity surfaces. To address this issue, our paper introduces a novel method that improves reconstruction by enforcing global geometry consistency through constrained multi-view triangulation. Our approach aims to achieve a consensus on 3D representation in the physical world by utilizing various estimated views. We optimize this process by penalizing the deviation of a rendered 3D point from a robust consensus point, which is re-triangulated from a bundle of neighboring views in a self-supervised fashion. We demonstrate the effectiveness of our method across multiple datasets, achieving state-of-the-art results. On the DTU dataset, our method attains a mean Chamfer Distance of 0.50 mm, outperforming comparable explicit methods. We will make our code open-source to facilitate community validation and ensure reproducibility.

Navigation is a fundamental capacity for mobile robots, enabling them to operate autonomously in complex and dynamic environments. Conventional approaches use probabilistic models to localize robots and build maps simultaneously using sensor observations. Recent approaches employ human-inspired learning, such as imitation and reinforcement learning, to navigate robots more effectively. However, these methods suffer from high computational costs, global map inconsistency, and poor generalization to unseen environments. This paper presents a novel method inspired by how humans perceive and navigate themselves effectively in novel environments. Specifically, we first build local frames that mimic how humans represent essential spatial information in the short term. Points in local frames are hybrid representations, including spatial information and learned features, so-called spatial-implicit local frames. Then, we integrate spatial-implicit local frames into the global topological map represented as a factor graph. Lastly, we developed a novel navigation algorithm based on Rapid-Exploring Random Tree Star (RRT*) that leverages spatial-implicit local frames and the topological map to navigate effectively in environments. To validate our approach, we conduct extensive experiments in real-world datasets and in-lab environments. We open our source code at https://github.com/tuantdang/simn.

Simultaneous localization and mapping (SLAM) in highly dynamic environments is challenging due to the correlation complexity between moving objects and the camera pose. Many methods have been proposed to deal with this problem; however, the moving properties of dynamic objects with a moving camera remain unclear. Therefore, to improve SLAM’s performance, minimizing disruptive events of moving objects with a physical understanding of 3D shapes and dynamics of objects is needed. In this paper, we propose a robust method, V3D-SLAM, to remove moving objects via two lightweight reevaluation stages, including identifying potentially moving and static objects using a spatial-reasoned Hough voting mechanism and refining static objects by detecting dynamic noise caused by intra-object motions using Chamfer distances as similarity measurements. Through our experiment on the TUM RGB-D benchmark on dynamic sequences with ground-truth camera trajectories, the results show that our methods outperform most other recent state-of-the-art SLAM methods. Our source code is available at https://github.com/tuantdang/v3d-slam.

Reconstructing three-dimensional (3D) scenes with semantic understanding is vital in many robotic applications. Robots need to identify which objects, along with their positions and shapes, to manipulate them precisely with given tasks. Mobile robots, especially, usually use lightweight networks to segment objects on RGB images and then localize them via depth maps; however, they often encounter out-of-distribution scenarios where masks over-cover the objects. In this paper, we address the problem of panoptic segmentation quality in 3D scene reconstruction by refining segmentation errors using non-parametric statistical methods. To enhance mask precision, we map the predicted masks into a depth frame to estimate their distribution via kernel densities. The outliers in depth perception are then rejected without the need for additional parameters in an adaptive manner to out-of-distribution scenarios, followed by 3D reconstruction using projective signed distance functions (SDFs). We validate our method on a synthetic dataset, which shows improvements in both quantitative and qualitative results for panoptic mapping. Through real-world testing, the results furthermore show our method’s capability to be deployed on a real-robot system. Our source code is available at: https://github.com/mkhangg/refined_panoptic_mapping.

Calibration is the first and foremost step in dealing with sensor displacement errors that can appear during extended operation and off-time periods to enable robot object manipulation with precision. In this paper, we present a novel multiplanar self-calibration between the camera system and the robot's end-effector for 3D object manipulation. Our approach first takes the robot end-effector as ground truth to calibrate the camera's position and orientation while the robot arm moves the object in multiple planes in 3D space, and a 2D state-of-the-art vision detector identifies the object's center in the image coordinates system. The transformation between world coordinates and image coordinates is then computed using 2D pixels from the detector and 3D known points obtained by robot kinematics. Next, an integrated stereo-vision system estimates the distance between the camera and the object, resulting in 3D object localization. We test our proposed method on the Baxter robot with two 7-DOF arms and a 2D detector that can run in real time on an onboard GPU. After self-calibrating, our robot can localize objects in 3D using an RGB camera and depth image. The source code is available at https://github.com/tuantdang/calib_cobot.

We present a low-maintenance, wind-powered, battery-free, biocompatible, tree wearable, and intelligent sensing system, namely IoTree, to monitor water and nutrient levels inside a living tree. IoTree system includes tiny-size, biocompatible, and implantable sensors that continuously measure the impedance variations inside the living tree's xylem, where water and nutrients are transported from the root to the upper parts. The collected data are then compressed and transmitted to a base station located at up to 1.8 kilometers (approximately 1.1 miles) away. The entire IoTree system is powered by wind energy and controlled by an adaptive computing technique called block-based intermittent computing, ensuring the forward progress and data consistency under intermittent power and allowing the firmware to execute with the most optimal memory and energy usage. We prototype IoTree that opportunistically performs sensing, data compression, and long-range communication tasks without batteries. During in-lab experiments, IoTree also obtains the accuracy of 91.08% and 90.51% in measuring 10 levels of nutrients, NH3 and K2O, respectively. While tested with Burkwood Viburnum and White Bird trees in the indoor environment, IoTree data strongly correlated with multiple watering and fertilizing events. We also deployed IoTree on a grapevine farm for 30 days, and the system is able to provide sufficient measurements every day.

In this paper, we present a low-maintenance, wind-powered, battery-free, biocompatible, tree wearable, and intelligent sensing system, namely IoTree, to monitor water and nutrient levels inside a living tree. IoTree system includes tiny-size, biocompatible, and implantable sensors that continuously measure the impedance variations inside the living tree's xylem, where water and nutrients are transported from the root to the upper parts. The collected data are then compressed and transmitted to a base station located at up to 1.8 kilometers (approximately 1.1 miles) away. The entire IoTree system is powered by wind energy and controlled by an adaptive computing technique called block-based intermittent computing, ensuring the forward progress and data consistency under intermittent power and allowing the firmware to execute with the most optimal memory and energy usage. We prototype IoTree that opportunistically performs sensing, data compression, and long-range communication tasks without batteries. During in-lab experiments, IoTree also obtains the accuracy of 91.08% and 90.51% in measuring 10 levels of nutrients, NH3 and K2O, respectively. While tested with Burkwood Viburnum and White Bird trees in the indoor environment, IoTree data strongly correlated with multiple watering and fertilizing events. We also deployed IoTree on a grapevine farm for 30 days, and the system is able to provide sufficient measurements every day.

Georgia Tech's Colleges of Engineering and Computing initiated the Vertically-Integrated Projects (VIP) program in January 2009. Undergraduate students that join VIP teams earn academic credit for participating in design efforts that assist faculty and graduate students with research and development issues in their technical areas. The teams are: multidisciplinary - drawing students from around the university; vertically-integrated - maintaining a mix of sophomores through PhD students each semester; and long-term - each undergraduate student may participate in a project for up to six semesters. We describe the Video and Image Annotation VIP (VIA-VIP) project, which provides undergraduates unique opportunities to learn and apply state-of-the-art video-mining algorithms by processing a large archive of football videos recorded from GT football games. Their results are documented. Based on their feedback we believe the VIA-VIP course is on track to meet the needs of undergraduates in areas they don't usually see in the traditional undergraduate classroom.

In this paper I present the so called Energy Web concepts and discuss its related technical challenges to overcome in order to make large scale renewable and distributed energy resources a true reality. Energy Web can be defined as a power ecosystem in which, information and communication technology (ICT), pulled up by the Web and the digital world, is going to revolutionize power markets, power distribution infrastructure and power on demand. The acceleration of ICT development and penetration in household electric equipment will provide enabling technology for making power on demand paradigm a reality. It will also catalyse more power efficiency applications. The road that leads to such power ecosystem is not very far but it has some technical barriers and challenges: a real-time metering standard and infrastructure, a real-time electricity pricing infrastructure, standardized distributed energy resources (DER) control and communication interface to the Energy Web network, price-smart responsive and adaptive power network nodes, "DER ready" power distribution network, resilient control strategy of system of systems. Facing such challenges, new scientific foundation and engineering methodology need to be developed to support the design, the simulation and the verification of expected resilient properties of the Energy Web infrastructure.

The work presented in this paper describes the concept of domain specific views (DSVs) according to which the specification of the control behavior is provided to the control developer. The basic idea is to investigate different application fields, to try to find common rules and models in different fields, and finally to build around this an automatic or semi-automatic transformation into executable code. The original idea is defined in a bigger aim that is the definition of a model oriented to the so-called ldquoautomation componentrdquo, used to standardize the design of an automation system. In the paper, the investigation is discussed for the discrete manufacturing and energy production fields, while in the main project (MEDEIA FP7-2007-211448) other fields are investigated and many languages and methodologies to develop control, diagnosis and simulation of automatic systems have been analyzed.