Dezhen Song

Yuantai Zhang, Jiaqi Yang, Huajian Zeng et al.

Fast and reliable initialization is critical for monocular visual-inertial navigation systems (VINS), as it establishes the starting conditions for subsequent state estimation. Despite steady progress, most existing methods heavily rely on visual feature correspondences and require 3-4 seconds of sensory data for successful initialization, which limits their applicability and efficiency. With the advent of feed-forward 3D models that can directly predict point clouds from images, we revisit the visual-inertial initialization problem from a concise perspective. In this work, we propose a feature-free initialization framework that leverages up-to-scale point clouds predicted by a feed-forward 3D model, thereby obviating the need for visual feature tracking and estimation. This design substantially reduces system complexity and improves the reliability of initialization. Experiments on public datasets demonstrate that the proposed feature-free initialization method achieves the highest success rate, exceeding 90%, and significantly reduces the data duration required for successful initialization, typically to under 1.2 s. We further validate our method on a self-collected dataset covering various indoor and outdoor scenarios, demonstrating robust performance, particularly in visually degraded environments where existing methods often fail. The code and dataset are available at https://github.com/Yuantai-Z/FF-VIO-Init.

Ibrahim Alsarraj, Yuhao Wang, Abdalla Swikir et al.

Tendon-driven continuum robots offer intrinsically safe and contact-rich interactions owing to their kinematic redundancy and structural compliance. However, their perception often depends on external sensors, which increase hardware complexity and limit scalability. This work introduces a unified multi-dynamics modeling framework for tendon-driven continuum robotic systems, exemplified by a spiral-inspired robot named Spirob. The framework integrates motor electrical dynamics, motor-winch dynamics, and continuum robot dynamics into a coherent system model. Within this framework, motor signals such as current and angular displacement are modeled to expose the electromechanical signatures of external interactions, enabling perception grounded in intrinsic dynamics. The model captures and validates key physical behaviors of the real system, including actuation hysteresis and self-contact at motion limits. Building on this foundation, the framework is applied to environmental interaction: first for passive contact detection, verified experimentally against simulation data; then for active contact sensing, where control and perception strategies from simulation are successfully applied to the real robot; and finally for object size estimation, where a policy learned in simulation is directly deployed on hardware. The results demonstrate that the proposed framework provides a physically grounded way to interpret interaction signatures from intrinsic motor signals in tendon-driven continuum robots.

Shu-Hao Yeh, Shuangyu Xie, Di Wang et al.

Optical Image Stabilization (OIS) system in mobile devices reduces image blurring by steering lens to compensate for hand jitters. However, OIS changes intrinsic camera parameters (i.e. $\mathrm{K}$ matrix) dynamically which hinders accurate camera pose estimation or 3D reconstruction. Here we propose a novel neural network-based approach that estimates $\mathrm{K}$ matrix in real-time so that pose estimation or scene reconstruction can be run at camera native resolution for the highest accuracy on mobile devices. Our network design takes gratified projection model discrepancy feature and 3D point positions as inputs and employs a Multi-Layer Perceptron (MLP) to approximate $f_{\mathrm{K}}$ manifold. We also design a unique training scheme for this network by introducing a Back propagated PnP (BPnP) layer so that reprojection error can be adopted as the loss function. The training process utilizes precise calibration patterns for capturing accurate $f_{\mathrm{K}}$ manifold but the trained network can be used anywhere. We name the proposed Dynamic Intrinsic Manifold Estimation network as DIME-Net and have it implemented and tested on three different mobile devices. In all cases, DIME-Net can reduce reprojection error by at least $64\%$ indicating that our design is successful.

Shuo Xing, Zezhou Sun, Shuangyu Xie et al.

In this paper, we introduce MapBench-the first dataset specifically designed for human-readable, pixel-based map-based outdoor navigation, curated from complex path finding scenarios. MapBench comprises over 1600 pixel space map path finding problems from 100 diverse maps. In MapBench, LVLMs generate language-based navigation instructions given a map image and a query with beginning and end landmarks. For each map, MapBench provides Map Space Scene Graph (MSSG) as an indexing data structure to convert between natural language and evaluate LVLM-generated results. We demonstrate that MapBench significantly challenges state-of-the-art LVLMs both zero-shot prompting and a Chain-of-Thought (CoT) augmented reasoning framework that decomposes map navigation into sequential cognitive processes. Our evaluation of both open-source and closed-source LVLMs underscores the substantial difficulty posed by MapBench, revealing critical limitations in their spatial reasoning and structured decision-making capabilities. We release all the code and dataset in https://github.com/taco-group/MapBench.

Quang P. M. Pham, Khoi T. N. Nguyen, Lan C. Ngo et al.

Scene graphs have proven to be highly effective for various scene understanding tasks due to their compact and explicit representation of relational information. However, current methods often overlook the critical importance of preserving symmetry when generating scene graphs from 3D point clouds, which can lead to reduced accuracy and robustness, particularly when dealing with noisy, multi-view data. Furthermore, a major limitation of prior approaches is the lack of temporal modeling to capture time-dependent relationships among dynamically evolving entities in a scene. To address these challenges, we propose Temporal Equivariant Scene Graph Neural Network (TESGNN), consisting of two key components: (1) an Equivariant Scene Graph Neural Network (ESGNN), which extracts information from 3D point clouds to generate scene graph while preserving crucial symmetry properties, and (2) a Temporal Graph Matching Network, which fuses scene graphs generated by ESGNN across multiple time sequences into a unified global representation using an approximate graph-matching algorithm. Our combined architecture TESGNN shown to be effective compared to existing methods in scene graph generation, achieving higher accuracy and faster training convergence. Moreover, we show that leveraging the symmetry-preserving property produces a more stable and accurate global scene representation compared to existing approaches. Finally, it is computationally efficient and easily implementable using existing frameworks, making it well-suited for real-time applications in robotics and computer vision. This approach paves the way for more robust and scalable solutions to complex multi-view scene understanding challenges. Our source code is publicly available at: https://github.com/HySonLab/TESGraph

Quang P. M. Pham, Khoi T. N. Nguyen, Nhi H. Doan et al.

Efficient path planning in robotics, particularly within large-scale, complex environments, remains a significant hurdle. While Large Language Models (LLMs) offer strong reasoning capabilities, their high computational cost and limited adaptability hinder real-time deployment on edge devices. We present SmallPlan - a novel framework leveraging LLMs as teacher models to train lightweight Small Language Models (SLMs) for high-level path planning tasks. In SmallPlan, the SLMs provide optimal action sequences to navigate across scene graphs that compactly represent full-scaled 3D scenes. The SLMs are trained in a simulation-powered, interleaved manner with LLM-guided supervised fine-tuning (SFT) and reinforcement learning (RL). This strategy not only enables SLMs to successfully complete navigation tasks but also makes them aware of important factors like distance travel, providing more efficient path planning. Through experiments, we demonstrate that the fine-tuned SLMs perform competitively with larger models like GPT-4o on sequential path planning, without suffering from hallucination and overfitting. SmallPlan is resource-efficient, making it well-suited for edge-device deployment and advancing practical autonomous robotics. Our source code is available here: https://github.com/quangpham2006/SmallPlan

Feng Lu, Baifan Chen, Xiang-Dong Zhou et al.

Recently, the methods based on Convolutional Neural Networks (CNNs) have gained popularity in the field of visual place recognition (VPR). In particular, the features from the middle layers of CNNs are more robust to drastic appearance changes than handcrafted features and high-layer features. Unfortunately, the holistic mid-layer features lack robustness to large viewpoint changes. Here we split the holistic mid-layer features into local features, and propose an adaptive dynamic time warping (DTW) algorithm to align local features from the spatial domain while measuring the distance between two images. This realizes viewpoint-invariant and condition-invariant place recognition. Meanwhile, a local matching DTW (LM-DTW) algorithm is applied to perform image sequence matching based on temporal alignment, which achieves further improvements and ensures linear time complexity. We perform extensive experiments on five representative VPR datasets. The results show that the proposed method significantly improves the CNN-based methods. Moreover, our method outperforms several state-of-the-art methods while maintaining good run-time performance. This work provides a novel way to boost the performance of CNN methods without any re-training for VPR. The code is available at https://github.com/Lu-Feng/STA-VPR.

Haoran Ding, Liang Ma, Yaxun Yang et al.

Visuomotor policies learned from demonstrations often overfit to nuisance visual factors in raw RGB observations, resulting in brittle behavior under appearance shifts such as background changes and object recoloring. We propose a task-aware observation interface that canonicalizes visual input into a shared representation, improving robustness to out-of-distribution (OOD) appearance changes without modifying or fine-tuning the policy. Given an RGB image and an open-vocabulary specification of task-relevant entities, we use SAM3 to segment the target object and robot/gripper. We construct an L0 observation by repainting segmented entities with predefined semantic colors on a constant background. For tasks requiring stronger geometric cues, we further inject monocular depth from Depth Anything 3 into the segmented regions via depth-guided overwrite, yielding a unified semantic--geometric observation (L1) that remains a standard 3-channel, image-like input. We evaluate on RoboMimic (Lift), ManiSkill YCB grasping under clutter, four RLBench tasks under controlled appearance shifts, and two real-world Franka tasks (ReachX and CloseCabinet). Across benchmarks and policy backbones (Flow Matching Policy and SmolVLA), our interface preserves in-distribution performance while substantially improving robustness under OOD visual shifts.

Huaichao Wang, Xuanxin Fan, Ji Liu et al.

When performing robot/vehicle localization using ground penetrating radar (GPR) to handle adverse weather and environmental conditions, existing techniques often struggle to accurately estimate distances when processing B-scan images with minor distinctions. This study introduces a new neural network-based odometry method that leverages the similarity and difference features of GPR B-scan images for precise estimation of the Euclidean distances traveled between the B-scan images. The new custom neural network extracts multi-scale features from B-scan images taken at consecutive moments and then determines the Euclidean distance traveled by analyzing the similarities and differences between these features. To evaluate our method, an ablation study and comparison experiments have been conducted using the publicly available CMU-GPR dataset. The experimental results show that our method consistently outperforms state-of-the-art counterparts in all tests. Specifically, our method achieves a root mean square error (RMSE), and achieves an overall weighted RMSE of 0.449 m across all data sets, which is a 10.2\% reduction in RMSE when compared to the best state-of-the-art method.

Peili Song, Dezhen Song, Yifan Yang et al.

Low-cost millimeter automotive radar has received more and more attention due to its ability to handle adverse weather and lighting conditions in autonomous driving. However, the lack of quality datasets hinders research and development. We report a new method that is able to simulate 4D millimeter wave radar signals including pitch, yaw, range, and Doppler velocity along with radar signal strength (RSS) using camera image, light detection and ranging (lidar) point cloud, and ego-velocity. The method is based on two new neural networks: 1) DIS-Net, which estimates the spatial distribution and number of radar signals, and 2) RSS-Net, which predicts the RSS of the signal based on appearance and geometric information. We have implemented and tested our method using open datasets from 3 different models of commercial automotive radar. The experimental results show that our method can successfully generate high-fidelity radar signals. Moreover, we have trained a popular object detection neural network with data augmented by our synthesized radar. The network outperforms the counterpart trained only on raw radar data, a promising result to facilitate future radar-based research and development.

Zohreh Shaghaghian, Heather Burte, Dezhen Song et al.

Despite the remarkable development of parametric modeling methods for architectural design, a significant problem still exists, which is the lack of knowledge and skill regarding the professional implementation of parametric design in architectural modeling. Considering the numerous advantages of digital/parametric modeling in rapid prototyping and simulation most instructors encourage students to use digital modeling even from the early stages of design; however, an appropriate context to learn the basics of digital design thinking is rarely provided in architectural pedagogy. This paper presents an educational tool, specifically an Augmented Reality (AR) intervention, to help students understand the fundamental concepts of para-metric modeling before diving into complex parametric modeling platforms. The goal of the AR intervention is to illustrate geometric transformation and the associated math functions so that students learn the mathematical logic behind the algorithmic thinking of parametric modeling. We have developed BRICKxAR_T, an educational AR prototype, that intends to help students learn geometric transformations in an immersive spatial AR environment. A LEGO set is used within the AR intervention as a physical manipulative to support physical interaction and im-prove spatial skill through body gesture.

Shuangyu Xie, Chengsong Hu, Muthukumar Bagavathiannan et al.

To enable robotic weed control, we develop algorithms to detect nutsedge weed from bermudagrass turf. Due to the similarity between the weed and the background turf, manual data labeling is expensive and error-prone. Consequently, directly applying deep learning methods for object detection cannot generate satisfactory results. Building on an instance detection approach (i.e. Mask R-CNN), we combine synthetic data with raw data to train the network. We propose an algorithm to generate high fidelity synthetic data, adopting different levels of annotations to reduce labeling cost. Moreover, we construct a nutsedge skeleton-based probabilistic map (NSPM) as the neural network input to reduce the reliance on pixel-wise precise labeling. We also modify loss function from cross entropy to Kullback-Leibler divergence which accommodates uncertainty in the labeling process. We implement the proposed algorithm and compare it with both Faster R-CNN and Mask R-CNN. The results show that our design can effectively overcome the impact of imprecise and insufficient training sample issues and significantly outperform the Faster R-CNN counterpart with a false negative rate of only 0.4%. In particular, our approach also reduces labeling time by 95% while achieving better performance if comparing with the original Mask R-CNN approach.

Zohreh Shaghaghian, Wei Yan, Dezhen Song

Despite the excessive developments of architectural parametric platforms, parametric design is often interpreted as an architectural style rather than a computational method. Also, the problem is still a lack of knowledge and skill about the technical application of parametric design in architectural modelling. Students often dive into utilizing complex digital modelling without having a competent pedagogical context to learn algorithmic thinking and the corresponding logic behind digital and parametric modelling. The insufficient skills and superficial knowledge often result in utilizing the modelling software through trial and error, not taking full advantage of what it has to offer. Geometric transformations as the fundamental functions of parametric modelling is explored in this study to anchor learning essential components in parametric modelling. Students need to understand the differences between variables, parameters, functions and their relations. Fologram, an Augmented Reality tool, is utilized in this study to learn geometric transformation and its components in an intuitive way. A LEGO set is used as an editable physical model to improve spatial skill through hand movement beside an instant feedback in the physical environment.

Kun Hu, Zhiyong Wang, Guy Coleman et al.

Weeds are a significant threat to the agricultural productivity and the environment. The increasing demand for sustainable agriculture has driven innovations in accurate weed control technologies aimed at reducing the reliance on herbicides. With the great success of deep learning in various vision tasks, many promising image-based weed detection algorithms have been developed. This paper reviews recent developments of deep learning techniques in the field of image-based weed detection. The review begins with an introduction to the fundamentals of deep learning related to weed detection. Next, recent progresses on deep weed detection are reviewed with the discussion of the research materials including public weed datasets. Finally, the challenges of developing practically deployable weed detection methods are summarized, together with the discussions of the opportunities for future research.We hope that this review will provide a timely survey of the field and attract more researchers to address this inter-disciplinary research problem.

Kuo Chen, Jingang Yi, Dezhen Song

Ranging from cart-pole systems and autonomous bicycles to bipedal robots, control of these underactuated balance robots aims to achieve both external (actuated) subsystem trajectory tracking and internal (unactuated) subsystem balancing tasks with limited actuation authority. This paper proposes a learning model-based control framework for underactuated balance robots. The key idea to simultaneously achieve tracking and balancing tasks is to design control strategies in slow- and fast-time scales, respectively. In slow-time scale, model predictive control (MPC) is used to generate the desired internal subsystem trajectory that encodes the external subsystem tracking performance and control input. In fast-time scale, the actual internal trajectory is stabilized to the desired internal trajectory by using an inverse dynamics controller. The coupling effects between the external and internal subsystems are captured through the planned internal trajectory profile and the dual structural properties of the robotic systems. The control design is based on Gaussian processes (GPs) regression model that are learned from experiments without need of priori knowledge about the robot dynamics nor successful balance demonstration. The GPs provide estimates of modeling uncertainties of the robotic systems and these uncertainty estimations are incorporated in the MPC design to enhance the control robustness to modeling errors. The learning-based control design is analyzed with guaranteed stability and performance. The proposed design is demonstrated by experiments on a Furuta pendulum and an autonomous bikebot.

Hsin-Min Cheng, Dezhen Song

Proprioceptive localization refers to a new class of robot egocentric localization methods that do not rely on the perception and recognition of external landmarks. These methods are naturally immune to bad weather, poor lighting conditions, or other extreme environmental conditions that may hinder exteroceptive sensors such as a camera or a laser ranger finder. These methods depend on proprioceptive sensors such as inertial measurement units (IMUs) and/or wheel encoders. Assisted by magnetoreception, the sensors can provide a rudimentary estimation of vehicle trajectory which is used to query a prior known map to obtain location. Named as graph-based proprioceptive localization (GBPL), we provide a low cost fallback solution for localization under challenging environmental conditions. As a robot/vehicle travels, we extract a sequence of heading-length values for straight segments from the trajectory and match the sequence with a pre-processed heading-length graph (HLG) abstracted from the prior known map to localize the robot under a graph-matching approach. Using the information from HLG, our location alignment and verification module compensates for trajectory drift, wheel slip, or tire inflation level. We have implemented our algorithm and tested it in both simulated and physical experiments. The algorithm runs successfully in finding robot location continuously and achieves localization accurate at the level that the prior map allows (less than 10m).

Shu-Hao Yeh, Dezhen Song

Robust estimation of camera motion under the presence of outlier noise is a fundamental problem in robotics and computer vision. Despite existing efforts that focus on detecting motion and scene degeneracies, the best existing approach that builds on Random Consensus Sampling (RANSAC) still has non-negligible failure rate. Since a single failure can lead to the failure of the entire visual simultaneous localization and mapping, it is important to further improve robust estimation algorithm. We propose a new robust camera motion estimator (RCME) by incorporating two main changes: model-sample consistence test at model instantiation step and inlier set quality test that verifies model-inlier consistence using differential entropy. We have implemented our RCME algorithm and tested it under many public datasets. The results have shown consistent reduction in failure rate when comparing to RANSAC-based Gold Standard approach. More specifically, the overall failure rate for indoor environments has reduced from 1.41% to 0.02%.

Ting Sun, Dezhen Song, Dit-Yan Yeung et al.

This paper presents a novel method to reduce the scale drift for indoor monocular simultaneous localization and mapping (SLAM). We leverage the prior knowledge that in the indoor environment, the line segments form tight clusters, e.g. many door frames in a straight corridor are of the same shape, size and orientation, so the same edges of these door frames form a tight line segment cluster. We implement our method in the popular ORB-SLAM2, which also serves as our baseline. In the front end we detect the line segments in each frame and incrementally cluster them in the 3D space. In the back end, we optimize the map imposing the constraint that the line segments of the same cluster should be the same. Experimental results show that our proposed method successfully reduces the scale drift for indoor monocular SLAM.