Anthony Tzes

Benjamin Kiefer, Matej Kristan, Janez Perš et al.

The 1$^{\text{st}}$ Workshop on Maritime Computer Vision (MaCVi) 2023 focused on maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicle (USV), and organized several subchallenges in this domain: (i) UAV-based Maritime Object Detection, (ii) UAV-based Maritime Object Tracking, (iii) USV-based Maritime Obstacle Segmentation and (iv) USV-based Maritime Obstacle Detection. The subchallenges were based on the SeaDronesSee and MODS benchmarks. This report summarizes the main findings of the individual subchallenges and introduces a new benchmark, called SeaDronesSee Object Detection v2, which extends the previous benchmark by including more classes and footage. We provide statistical and qualitative analyses, and assess trends in the best-performing methodologies of over 130 submissions. The methods are summarized in the appendix. The datasets, evaluation code and the leaderboard are publicly available at https://seadronessee.cs.uni-tuebingen.de/macvi.

Sotiris Papatheodorou, Anthony Tzes, Yiannis Stergiopoulos

This article examines the problem of visual area coverage by a network of Mobile Aerial Agents (MAAs). Each MAA is assumed to be equipped with a downwards facing camera with a conical field of view which covers all points within a circle on the ground. The diameter of that circle is proportional to the altitude of the MAA, whereas the quality of the covered area decreases with the altitude. A distributed control law that maximizes a joint coverage-quality criterion by adjusting the MAAs' spatial coordinates is developed. The effectiveness of the proposed control scheme is evaluated through simulation studies.

Daitao Xing, Jinglin Shen, Chiuman Ho et al.

The exploration of mutual-benefit cross-domains has shown great potential toward accurate self-supervised depth estimation. In this work, we revisit feature fusion between depth and semantic information and propose an efficient local adaptive attention method for geometric aware representation enhancement. Instead of building global connections or deforming attention across the feature space without restraint, we bound the spatial interaction within a learnable region of interest. In particular, we leverage geometric cues from semantic information to learn local adaptive bounding boxes to guide unsupervised feature aggregation. The local areas preclude most irrelevant reference points from attention space, yielding more selective feature learning and faster convergence. We naturally extend the paradigm into a multi-head and hierarchic way to enable the information distillation in different semantic levels and improve the feature discriminative ability for fine-grained depth estimation. Extensive experiments on the KITTI dataset show that our proposed method establishes a new state-of-the-art in self-supervised monocular depth estimation task, demonstrating the effectiveness of our approach over former Transformer variants.

Sotiris Papatheodorou, Anthony Tzes, Yiannis Stergiopoulos

This article addresses the visual area coverage problem using a team of Unmanned Aerial Vehicles (UAVs). The UAVs are assumed to be equipped with a downward facing camera covering all points of interest within a circle on the ground. The diameter of this circular conic-section increases as the UAV flies at a larger height, yet the quality of the observed area is inverse proportional to the UAV's height. The objective is to provide a distributed control algorithm that maximizes a combined coverage-quality criterion by adjusting the UAV's altitude. Simulation studies are offered to highlight the effectiveness of the suggested scheme.

Omar Alfarisi, Zeyar Aung, Qingfeng Huang et al.

Planetary exploration depends heavily on 3D image data to characterize the static and dynamic properties of the rock and environment. Analyzing 3D images requires many computations, causing efficiency to suffer lengthy processing time alongside large energy consumption. High-Performance Computing (HPC) provides apparent efficiency at the expense of energy consumption. However, for remote explorations, the conveyed surveillance and the robotized sensing need faster data analysis with ultimate accuracy to make real-time decisions. In such environments, access to HPC and energy is limited. Therefore, we realize that reducing the number of computations to optimal and maintaining the desired accuracy leads to higher efficiency. This paper demonstrates the semantic segmentation capability of a probabilistic decision tree algorithm, 3D Adapted Random Forest Vision (3DARFV), exceeding deep learning algorithm efficiency at the utmost accuracy.

Wenqi Cai, Kyriakos G. Vamvoudakis, Sébastien Gros et al.

In this paper, we propose a cost-matching approach for optimal humanoid locomotion within a Model Predictive Control (MPC)-based Reinforcement Learning (RL) framework. A parameterized MPC formulation with centroidal dynamics is trained to approximate the action-value function obtained from high-fidelity closed-loop data. Specifically, the MPC cost-to-go is evaluated along recorded state-action trajectories, and the parameters are updated to minimize the discrepancy between MPC-predicted values and measured returns. This formulation enables efficient gradient-based learning while avoiding the computational burden of repeatedly solving the MPC problem during training. The proposed method is validated in simulation using a commercial humanoid platform. Results demonstrate improved locomotion performance and robustness to model mismatch and external disturbances compared with manually tuned baselines.

Wenqi Cai, John Abanes, Nikolaos Evangeliou et al.

Ensuring operational safety is critical for human-to-humanoid motion imitation. This paper presents a vision-based framework that enables a humanoid robot to imitate human movements while avoiding collisions. Human skeletal keypoints are captured by a single camera and converted into joint angles for motion retargeting. Safety is enforced through a Control Barrier Function (CBF) layer formulated as a Quadratic Program (QP), which filters imitation commands to prevent both self-collisions and human-robot collisions. Simulation results validate the effectiveness of the proposed framework for real-time collision-aware motion imitation.

Daitao Xing, Nikolaos Evangeliou, Athanasios Tsoukalas et al.

Recent object tracking methods depend upon deep networks or convoluted architectures. Most of those trackers can hardly meet real-time processing requirements on mobile platforms with limited computing resources. In this work, we introduce the Siamese Transformer Pyramid Network (SiamTPN), which inherits the advantages from both CNN and Transformer architectures. Specifically, we exploit the inherent feature pyramid of a lightweight network (ShuffleNetV2) and reinforce it with a Transformer to construct a robust target-specific appearance model. A centralized architecture with lateral cross attention is developed for building augmented high-level feature maps. To avoid the computation and memory intensity while fusing pyramid representations with the Transformer, we further introduce the pooling attention module, which significantly reduces memory and time complexity while improving the robustness. Comprehensive experiments on both aerial and prevalent tracking benchmarks achieve competitive results while operating at high speed, demonstrating the effectiveness of SiamTPN. Moreover, our fastest variant tracker operates over 30 Hz on a single CPU-core and obtaining an AUC score of 58.1% on the LaSOT dataset. Source codes are available at https://github.com/RISCNYUAD/SiamTPNTracker

Congcong Wen, Jiazhao Liang, Shuaihang Yuan et al.

In the field of robotics and automation, navigation systems based on Large Language Models (LLMs) have recently demonstrated impressive performance. However, the security aspects of these systems have received relatively less attention. This paper pioneers the exploration of vulnerabilities in LLM-based navigation models in urban outdoor environments, a critical area given the widespread application of this technology in autonomous driving, logistics, and emergency services. Specifically, we introduce a novel Navigational Prompt Attack that manipulates LLM-based navigation models by perturbing the original navigational prompt, leading to incorrect actions. Based on the method of perturbation, our attacks are divided into two types: Navigational Prompt Insert (NPI) Attack and Navigational Prompt Swap (NPS) Attack. We conducted comprehensive experiments on an LLM-based navigation model that employs various LLMs for reasoning. Our results, derived from the Touchdown and Map2Seq street-view datasets under both few-shot learning and fine-tuning configurations, demonstrate notable performance declines across seven metrics in the face of both white-box and black-box attacks. Moreover, our attacks can be easily extended to other LLM-based navigation models with similarly effective results. These findings highlight the generalizability and transferability of the proposed attack, emphasizing the need for enhanced security in LLM-based navigation systems. As an initial countermeasure, we propose the Navigational Prompt Engineering (NPE) Defense strategy, which concentrates on navigation-relevant keywords to reduce the impact of adversarial attacks. While initial findings indicate that this strategy enhances navigational safety, there remains a critical need for the wider research community to develop stronger defense methods to effectively tackle the real-world challenges faced by these systems.

Congcong Wen, Geeta Chandra Raju Bethala, Yu Hao et al.

Humanoid loco-manipulation, which integrates whole-body locomotion with dexterous manipulation, remains a fundamental challenge in robotics. Beyond whole-body coordination and balance, a central difficulty lies in understanding human instructions and translating them into coherent sequences of embodied actions. Recent advances in foundation models provide transferable multimodal representations and reasoning capabilities, yet existing efforts remain largely restricted to either locomotion or manipulation in isolation, with limited applicability to humanoid settings. In this paper, we propose Humanoid-COA, the first humanoid agent framework that integrates foundation model reasoning with an Embodied Chain-of-Action (CoA) mechanism for zero-shot loco-manipulation. Within the perception--reasoning--action paradigm, our key contribution lies in the reasoning stage, where the proposed CoA mechanism decomposes high-level human instructions into structured sequences of locomotion and manipulation primitives through affordance analysis, spatial inference, and whole-body action reasoning. Extensive experiments on two humanoid robots, Unitree H1-2 and G1, in both an open test area and an apartment environment, demonstrate that our framework substantially outperforms prior baselines across manipulation, locomotion, and loco-manipulation tasks, achieving robust generalization to long-horizon and unstructured scenarios. Project page: https://humanoid-coa.github.io/

Yijie Deng, Shuaihang Yuan, Geeta Chandra Raju Bethala et al.

Instance Image-Goal Navigation (IIN) requires autonomous agents to identify and navigate to a target object or location depicted in a reference image captured from any viewpoint. While recent methods leverage powerful novel view synthesis (NVS) techniques, such as three-dimensional Gaussian splatting (3DGS), they typically rely on randomly sampling multiple viewpoints or trajectories to ensure comprehensive coverage of discriminative visual cues. This approach, however, creates significant redundancy through overlapping image samples and lacks principled view selection, substantially increasing both rendering and comparison overhead. In this paper, we introduce a novel IIN framework with a hierarchical scoring paradigm that estimates optimal viewpoints for target matching. Our approach integrates cross-level semantic scoring, utilizing CLIP-derived relevancy fields to identify regions with high semantic similarity to the target object class, with fine-grained local geometric scoring that performs precise pose estimation within promising regions. Extensive evaluations demonstrate that our method achieves state-of-the-art performance on simulated IIN benchmarks and real-world applicability.

Halil Utku Unlu, Shuaihang Yuan, Congcong Wen et al.

We introduce an innovative approach to advancing semantic understanding in zero-shot object goal navigation (ZS-OGN), enhancing the autonomy of robots in unfamiliar environments. Traditional reliance on labeled data has been a limitation for robotic adaptability, which we address by employing a dual-component framework that integrates a GLIP Vision Language Model for initial detection and an InstructionBLIP model for validation. This combination not only refines object and environmental recognition but also fortifies the semantic interpretation, pivotal for navigational decision-making. Our method, rigorously tested in both simulated and real-world settings, exhibits marked improvements in navigation precision and reliability.

Shuaihang Yuan, Congcong Wen, Muhammad Shafique et al.

The rapid advances in audio analysis underscore its vast potential for humancomputer interaction, environmental monitoring, and public safety; yet, existing audioonly datasets often lack spatial context. To address this gap, we present two novel audiospatial scene datasets, AudioScanNet and AudioRoboTHOR, designed to explore audioconditioned tasks within 3D environments. By integrating audio clips with spatially aligned 3D scenes, our datasets enable research on how audio signals interact with spatial context. To associate audio events with corresponding spatial information, we leverage the common sense reasoning ability of large language models and supplement them with rigorous human verification, This approach offers greater scalability compared to purely manual annotation while maintaining high standards of accuracy, completeness, and diversity, quantified through inter annotator agreement and performance on two benchmark tasks audio based 3D visual grounding and audio based robotic zeroshot navigation. The results highlight the limitations of current audiocentric methods and underscore the practical challenges and significance of our datasets in advancing audio guided spatial learning.

Hao Huang, Geeta Chandra Raju Bethala, Shuaihang Yuan et al.

Whole-body humanoid motion represents a cornerstone challenge in robotics, integrating balance, coordination, and adaptability to enable human-like behaviors. However, existing methods typically require multiple training samples per motion category, rendering the collection of high-quality human motion datasets both labor-intensive and costly. To address this, we propose a novel approach that trains effective humanoid motion policies using only a single non-walking target motion sample alongside readily available walking motions. The core idea lies in leveraging order-preserving optimal transport to compute distances between walking and non-walking sequences, followed by interpolation along geodesics to generate new intermediate pose skeletons, which are then optimized for collision-free configurations and retargeted to the humanoid before integration into a simulated environment for policy training via reinforcement learning. Experimental evaluations on the CMU MoCap dataset demonstrate that our method consistently outperforms baselines, achieving superior performance across metrics. Code will be released upon acceptance.

Omar Rayyan, John Abanes, Mahmoud Hafez et al.

Recent advances in imitation learning have shown great promise for developing robust robot manipulation policies from demonstrations. However, this promise is contingent on the availability of diverse, high-quality datasets, which are not only challenging and costly to collect but are often constrained to a specific robot embodiment. Portable handheld grippers have recently emerged as intuitive and scalable alternatives to traditional robotic teleoperation methods for data collection. However, their reliance solely on first-person view wrist-mounted cameras often creates limitations in capturing sufficient scene contexts. In this paper, we present MV-UMI (Multi-View Universal Manipulation Interface), a framework that integrates a third-person perspective with the egocentric camera to overcome this limitation. This integration mitigates domain shifts between human demonstration and robot deployment, preserving the cross-embodiment advantages of handheld data-collection devices. Our experimental results, including an ablation study, demonstrate that our MV-UMI framework improves performance in sub-tasks requiring broad scene understanding by approximately 47% across 3 tasks, confirming the effectiveness of our approach in expanding the range of feasible manipulation tasks that can be learned using handheld gripper systems, without compromising the cross-embodiment advantages inherent to such systems.

Yijie Deng, Shuaihang Yuan, Congcong Wen et al.

Spatial awareness is a critical capability for embodied agents, as it enables them to anticipate and reason about unobserved regions. The primary challenge arises from learning the distribution of indoor semantics, complicated by sparse, imbalanced object categories and diverse spatial scales. Existing methods struggle to robustly generate unobserved areas in real time and do not generalize well to new environments. To this end, we propose \textbf{MapBERT}, a novel framework designed to effectively model the distribution of unseen spaces. Motivated by the observation that the one-hot encoding of semantic maps aligns naturally with the binary structure of bit encoding, we, for the first time, leverage a lookup-free BitVAE to encode semantic maps into compact bitwise tokens. Building on this, a masked transformer is employed to infer missing regions and generate complete semantic maps from limited observations. To enhance object-centric reasoning, we propose an object-aware masking strategy that masks entire object categories concurrently and pairs them with learnable embeddings, capturing implicit relationships between object embeddings and spatial tokens. By learning these relationships, the model more effectively captures indoor semantic distributions crucial for practical robotic tasks. Experiments on Gibson benchmarks show that MapBERT achieves state-of-the-art semantic map generation, balancing computational efficiency with accurate reconstruction of unobserved regions.

Halil Utku Unlu, Anthony Tzes, Prashanth Krishnamurthy et al.

A robust, resource-efficient, distributed, and minimally parameterized 3D map matching and merging algorithm is proposed. The suggested algorithm utilizes tomographic features from 2D projections of horizontal cross-sections of gravity-aligned local maps, and matches these projection slices at all possible height differences, enabling the estimation of four degrees of freedom in an efficient and parallelizable manner. The advocated algorithm improves state-of-the-art feature extraction and registration pipelines by an order of magnitude in memory use and execution time. Experimental studies are offered to investigate the efficiency of this 3D map merging scheme.

Shuaihang Yuan, Xiang Li, Anthony Tzes et al.

In this paper, we deal with the problem to predict the future 3D motions of 3D object scans from previous two consecutive frames. Previous methods mostly focus on sparse motion prediction in the form of skeletons. While in this paper we focus on predicting dense 3D motions in the from of 3D point clouds. To approach this problem, we propose a self-supervised approach that leverages the power of the deep neural network to learn a continuous flow function of 3D point clouds that can predict temporally consistent future motions and naturally bring out the correspondences among consecutive point clouds at the same time. More specifically, in our approach, to eliminate the unsolved and challenging process of defining a discrete point convolution on 3D point cloud sequences to encode spatial and temporal information, we introduce a learnable latent code to represent the temporal-aware shape descriptor which is optimized during model training. Moreover, a temporally consistent motion Morpher is proposed to learn a continuous flow field which deforms a 3D scan from the current frame to the next frame. We perform extensive experiments on D-FAUST, SCAPE and TOSCA benchmark data sets and the results demonstrate that our approach is capable of handling temporally inconsistent input and produces consistent future 3D motion while requiring no ground truth supervision.

Steffen Holter, Athanasios Tsoukalas, Nikolaos Evangeliou et al.

Cooperative Unmanned Aerial Systems (UASs) in GPS-denied environments demand an accurate pose-localization system to ensure efficient operation. In this paper we present a novel visual relative localization system capable of monitoring a 360$^o$ Field-of-View (FoV) in the immediate surroundings of the UAS using a spherical camera. Collaborating UASs carry a set of fiducial markers which are detected by the camera-system. The spherical image is partitioned and rectified into a set of square images. An algorithm is proposed to select the number of images that balances the computational load while maintaining a minimum tracking-accuracy level. The developed system tracks UASs in the vicinity of the spherical camera and experimental studies using two UASs are offered to validate the performance of the relative visual localization against that of a motion capture system.

Kostas Alexis, Christos Papachristos, Roland Siegwart et al.

Within this paper, the problem of 3D structural inspection path planning for distributed infrastructure using aerial robots that are subject to time constraints is addressed. The proposed algorithm handles varying spatial properties of the infrastructure facilities, accounts for their different importance and exploration function and computes an overall inspection path of high inspection reward while respecting the robot endurance or mission time constraints as well as the vehicle dynamics and sensor limitations. To achieve its goal, it employs an iterative, 3-step optimization strategy at each iteration of which it first randomly samples a set of possible structures to visit, subsequently solves the derived traveling salesman problem and computes the travel costs, while finally it samples and assigns inspection times to each structure and evaluates the total inspection reward. For the derivation of the inspection paths per each independent facility, it interfaces a path planner dedicated to the 3D coverage of single structures. The resulting algorithm properties, computational performance and path quality are evaluated using simulation studies as well as experimental test-cases employing a multirotor micro aerial vehicle.

Sotiris Papatheodorou, Anthony Tzes, Konstantinos Giannousakis et al.

This article examines the area coverage problem for a network of mobile robots with imprecise agents' localization. Each robot has uniform radial sensing ability, governed by first order kinodynamics. The convex-space is partitioned based on the Guaranteed Voronoi (GV) principle and each robot's area of responsibility corresponds to its GV-cell, bounded by hyperbolic arcs. The proposed control law is distributed, demanding the positioning information about its GV-Delaunay neighbors. Simulation and experimental studies are offered to highlight the efficiency of the proposed control law.