arXiv subjects

Kostas Alexis

Publications and source records attributed to Kostas Alexis.

At least 37 records · Page 2Linked to original sources

arXiv2026

Cross-Modal Reinforcement Learning for Navigation with Degraded Depth Measurements

This paper presents a cross-modal learning framework that exploits complementary information from depth and grayscale images for robust navigation. We introduce a Cross-Modal Wasserstein Autoencoder that learns shared latent representations by enforcing cross-modal consistency, enabling the system to infer depth-relevant features from grayscale observations when depth measurements are corrupted. The learned representations are integrated with a Reinforcement Learning-based policy for collision-free navigation in unstructured environments when depth sensors experience degradation due to adverse conditions such as poor lighting or reflective surfaces. Simulation and real-world experiments demonstrate that our approach maintains robust performance under significant depth degradation and successfully transfers to real environments.

cs.RO↗

arXiv2026

Efficient Knowledge Transfer for Jump-Starting Control Policy Learning of Multirotors through Physics-Aware Neural Architectures

Efficiently training control policies for robots is a major challenge that can greatly benefit from utilizing knowledge gained from training similar systems through cross-embodiment knowledge transfer. In this work, we focus on accelerating policy training using a library-based initialization scheme that enables effective knowledge transfer across multirotor configurations. By leveraging a physics-aware neural control architecture that combines a reinforcement learning-based controller and a supervised control allocation network, we enable the reuse of previously trained policies. To this end, we utilize a policy evaluation-based similarity measure that identifies suitable policies for initialization from a library. We demonstrate that this measure correlates with the reduction in environment interactions needed to reach target performance and is therefore suited for initialization. Extensive simulation and real-world experiments confirm that our control architecture achieves state-of-the-art control performance, and that our initialization scheme saves on average up to $73.5\%$ of environment interactions (compared to training a policy from scratch) across diverse quadrotor and hexarotor designs, paving the way for efficient cross-embodiment transfer in reinforcement learning.

cs.RO↗

arXiv2026

Relationship-Aware Hierarchical 3D Scene Graph for Task Reasoning

Representing and understanding 3D environments in a structured manner is crucial for autonomous agents to navigate and reason about their surroundings. While traditional Simultaneous Localization and Mapping (SLAM) methods generate metric reconstructions and can be extended to metric-semantic mapping, they lack a higher level of abstraction and relational reasoning. To address this gap, 3D scene graphs have emerged as a powerful representation for capturing hierarchical structures and object relationships. In this work, we propose an enhanced hierarchical 3D scene graph that integrates open-vocabulary features across multiple abstraction levels and supports object-relational reasoning. Our approach leverages a Vision Language Model (VLM) to infer semantic relationships. Notably, we introduce a task reasoning module that combines Large Language Models (LLM) and a VLM to interpret the scene graph's semantic and relational information, enabling agents to reason about tasks and interact with their environment more intelligently. We validate our method by deploying it on a quadruped robot in multiple environments and tasks, highlighting its ability to reason about them.

cs.RO↗

arXiv2026

Reinforcement Learning for Active Perception in Autonomous Navigation

This paper addresses the challenge of active perception within autonomous navigation in complex, unknown environments. Revisiting the foundational principles of active perception, we introduce an end-to-end reinforcement learning framework in which a robot must not only reach a goal while avoiding obstacles, but also actively control its onboard camera to enhance situational awareness. The policy receives observations comprising the robot state, the current depth frame, and a particularly local geometry representation built from a short history of depth readings. To couple collision-free motion planning with information-driven active camera control, we augment the navigation reward with a voxel-based information metric. This enables an aerial robot to learn a robust policy that balances goal-directed motion with exploratory sensing. Extensive evaluation demonstrates that our strategy achieves safer flight compared to using fixed, non-actuated camera baselines while also inducing intrinsic exploratory behaviors.

cs.RO↗

arXiv2025

Neural NMPC through Signed Distance Field Encoding for Collision Avoidance

This paper introduces a neural Nonlinear Model Predictive Control (NMPC) framework for mapless, collision-free navigation in unknown environments with Aerial Robots, using onboard range sensing. We leverage deep neural networks to encode a single range image, capturing all the available information about the environment, into a Signed Distance Function (SDF). The proposed neural architecture consists of two cascaded networks: a convolutional encoder that compresses the input image into a low-dimensional latent vector, and a Multi-Layer Perceptron that approximates the corresponding spatial SDF. This latter network parametrizes an explicit position constraint used for collision avoidance, which is embedded in a velocity-tracking NMPC that outputs thrust and attitude commands to the robot. First, a theoretical analysis of the contributed NMPC is conducted, verifying recursive feasibility and stability properties under fixed observations. Subsequently, we evaluate the open-loop performance of the learning-based components as well as the closed-loop performance of the controller in simulations and experiments. The simulation study includes an ablation study, comparisons with two state-of-the-art local navigation methods, and an assessment of the resilience to drifting odometry. The real-world experiments are conducted in forest environments, demonstrating that the neural NMPC effectively performs collision avoidance in cluttered settings against an adversarial reference velocity input and drifting position estimates.

cs.RO↗

arXiv2025

Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning

We present Isaac Lab, the natural successor to Isaac Gym, which extends the paradigm of GPU-native robotics simulation into the era of large-scale multi-modal learning. Isaac Lab combines high-fidelity GPU parallel physics, photorealistic rendering, and a modular, composable architecture for designing environments and training robot policies. Beyond physics and rendering, the framework integrates actuator models, multi-frequency sensor simulation, data collection pipelines, and domain randomization tools, unifying best practices for reinforcement and imitation learning at scale within a single extensible platform. We highlight its application to a diverse set of challenges, including whole-body control, cross-embodiment mobility, contact-rich and dexterous manipulation, and the integration of human demonstrations for skill acquisition. Finally, we discuss upcoming integration with the differentiable, GPU-accelerated Newton physics engine, which promises new opportunities for scalable, data-efficient, and gradient-based approaches to robot learning. We believe Isaac Lab's combination of advanced simulation capabilities, rich sensing, and data-center scale execution will help unlock the next generation of breakthroughs in robotics research.

cs.RO↗

arXiv2025

Towards Quadrupedal Jumping and Walking for Dynamic Locomotion using Reinforcement Learning

This paper presents a curriculum-based reinforcement learning framework for training precise and high-performance jumping policies for the robot `Olympus'. Separate policies are developed for vertical and horizontal jumps, leveraging a simple yet effective strategy. First, we densify the inherently sparse jumping reward using the laws of projectile motion. Next, a reference state initialization scheme is employed to accelerate the exploration of dynamic jumping behaviors without reliance on reference trajectories. We also present a walking policy that, when combined with the jumping policies, unlocks versatile and dynamic locomotion capabilities. Comprehensive testing validates walking on varied terrain surfaces and jumping performance that exceeds previous works, effectively crossing the Sim2Real gap. Experimental validation demonstrates horizontal jumps up to 1.25 m with centimeter accuracy and vertical jumps up to 1.0 m. Additionally, we show that with only minor modifications, the proposed method can be used to learn omnidirectional jumping.

cs.RO↗

arXiv2025

Diffusion-based RGB-D Semantic Segmentation with Deformable Attention Transformer

Vision-based perception and reasoning is essential for scene understanding in any autonomous system. RGB and depth images are commonly used to capture both the semantic and geometric features of the environment. Developing methods to reliably interpret this data is critical for real-world applications, where noisy measurements are often unavoidable. In this work, we introduce a diffusion-based framework to address the RGB-D semantic segmentation problem. Additionally, we demonstrate that utilizing a Deformable Attention Transformer as the encoder to extract features from depth images effectively captures the characteristics of invalid regions in depth measurements. Our generative framework shows a greater capacity to model the underlying distribution of RGB-D images, achieving robust performance in challenging scenarios with significantly less training time compared to discriminative methods. Experimental results indicate that our approach achieves State-of-the-Art performance on both the NYUv2 and SUN-RGBD datasets in general and especially in the most challenging of their image data. Our project page will be available at https://diffusionmms.github.io/

cs.CV↗

arXiv2025

IMU-Preintegrated Radar Factors for Asynchronous Radar-LiDAR-Inertial SLAM

Fixed-lag Radar-LiDAR-Inertial smoothers conventionally create one factor graph node per measurement to compensate for the lack of time synchronization between radar and LiDAR. For a radar-LiDAR sensor pair with equal rates, this strategy results in a state creation rate of twice the individual sensor frequencies. This doubling of the number of states per second yields high optimization costs, inhibiting real-time performance on resource-constrained hardware. We introduce IMU-preintegrated radar factors that use high-rate inertial data to propagate the most recent LiDAR state to the radar measurement timestamp. This strategy maintains the node creation rate at the LiDAR measurement frequency. Assuming equal sensor rates, this lowers the number of nodes by 50 % and consequently the computational costs. Experiments on a single board computer (which has 4 cores each of 2.2 GHz A73 and 2 GHz A53 with 8 GB RAM) show that our method preserves the absolute pose error of a conventional baseline while simultaneously lowering the aggregated factor graph optimization time by up to 56 %.

cs.RO↗

arXiv2025

UniPilot: Enabling GPS-Denied Autonomy Across Embodiments

This paper presents UniPilot, a compact hardware-software autonomy payload that can be integrated across diverse robot embodiments to enable autonomous operation in GPS-denied environments. The system integrates a multi-modal sensing suite including LiDAR, radar, vision, and inertial sensing for robust operation in conditions where uni-modal approaches may fail. UniPilot runs a complete autonomy software comprising multi-modal perception, exploration and inspection path planning, and learning-based navigation policies. The payload provides robust localization, mapping, planning, and safety and control capabilities in a single unit that can be deployed across a wide range of platforms. A large number of experiments are conducted across diverse environments and on a variety of robot platforms to validate the mapping, planning, and safe navigation capabilities enabled by the payload.

cs.RO↗

arXiv2025

Collaborative Exploration with a Marsupial Ground-Aerial Robot Team through Task-Driven Map Compression

Efficient exploration of unknown environments is crucial for autonomous robots, especially in confined and large-scale scenarios with limited communication. To address this challenge, we propose a collaborative exploration framework for a marsupial ground-aerial robot team that leverages the complementary capabilities of both platforms. The framework employs a graph-based path planning algorithm to guide exploration and deploy the aerial robot in areas where its expected gain significantly exceeds that of the ground robot, such as large open spaces or regions inaccessible to the ground platform, thereby maximizing coverage and efficiency. To facilitate large-scale spatial information sharing, we introduce a bandwidth-efficient, task-driven map compression strategy. This method enables each robot to reconstruct resolution-specific volumetric maps while preserving exploration-critical details, even at high compression rates. By selectively compressing and sharing key data, communication overhead is minimized, ensuring effective map integration for collaborative path planning. Simulation and real-world experiments validate the proposed approach, demonstrating its effectiveness in improving exploration efficiency while significantly reducing data transmission.

cs.RO↗

arXiv2025

Uncertainty Aware Mapping for Vision-Based Underwater Robots

Vision-based underwater robots can be useful in inspecting and exploring confined spaces where traditional sensors and preplanned paths cannot be followed. Sensor noise and situational change can cause significant uncertainty in environmental representation. Thus, this paper explores how to represent mapping inconsistency in vision-based sensing and incorporate depth estimation confidence into the mapping framework. The scene depth and the confidence are estimated using the RAFT-Stereo model and are integrated into a voxel-based mapping framework, Voxblox. Improvements in the existing Voxblox weight calculation and update mechanism are also proposed. Finally, a qualitative analysis of the proposed method is performed in a confined pool and in a pier in the Trondheim fjord. Experiments using an underwater robot demonstrated the change in uncertainty in the visualization.

cs.RO↗

arXiv2025

Ariel Explores: Vision-based underwater exploration and inspection via generalist drone-level autonomy

This work presents a vision-based underwater exploration and inspection autonomy solution integrated into Ariel, a custom vision-driven underwater robot. Ariel carries a $5$ camera and IMU based sensing suite, enabling a refraction-aware multi-camera visual-inertial state estimation method aided by a learning-based proprioceptive robot velocity prediction method that enhances robustness against visual degradation. Furthermore, our previously developed and extensively field-verified autonomous exploration and general visual inspection solution is integrated on Ariel, providing aerial drone-level autonomy underwater. The proposed system is field-tested in a submarine dry dock in Trondheim under challenging visual conditions. The field demonstration shows the robustness of the state estimation solution and the generalizability of the path planning techniques across robot embodiments.

cs.RO↗

arXiv2025

Simultaneous Triggering and Synchronization of Sensors and Onboard Computers

High fidelity estimation algorithms for robotics require accurate data. However, timestamping of sensor data is a key issue that rarely receives the attention it deserves. Inaccurate timestamping can be compensated for in post-processing but is imperative for online estimation. Simultaneously, even online mitigation of timing issues can be achieved through a relaxation of the tuning parameters from their otherwise more performative optimal values, but at a detriment to performance. To address the need for real-time, low-cost timestamping, a versatile system which utilizes readily-available components and established methods for synchronization is introduced. The synchronization and triggering (of both high- and low-rate sensors) capabilities of the system are demonstrated.

cs.RO↗

arXiv2025

PG-LIO: Photometric-Geometric fusion for Robust LiDAR-Inertial Odometry

LiDAR-Inertial Odometry (LIO) is widely used for accurate state estimation and mapping which is an essential requirement for autonomous robots. Conventional LIO methods typically rely on formulating constraints from the geometric structure sampled by the LiDAR. Hence, in the lack of geometric structure, these tend to become ill-conditioned (degenerate) and fail. Robustness of LIO to such conditions is a necessity for its broader deployment. To address this, we propose PG-LIO, a real-time LIO method that fuses photometric and geometric information sampled by the LiDAR along with inertial constraints from an Inertial Measurement Unit (IMU). This multi-modal information is integrated into a factor graph optimized over a sliding window for real-time operation. We evaluate PG-LIO on multiple datasets that include both geometrically well-conditioned as well as self-similar scenarios. Our method achieves accuracy on par with state-of-the-art LIO in geometrically well-structured settings while significantly improving accuracy in degenerate cases including against methods that also fuse intensity. Notably, we demonstrate only 1 m drift over a 1 km manually piloted aerial trajectory through a geometrically self-similar tunnel at an average speed of 7.5m/s (max speed 10.8 m/s). For the benefit of the community, we shall also release our source code https://github.com/ntnu-arl/mimosa

cs.RO↗

arXiv2025

Semantics-aware Predictive Inspection Path Planning

This paper presents a novel semantics-aware inspection path planning paradigm called "Semantics-aware Predictive Planning" (SPP). Industrial environments that require the inspection of specific objects or structures (called "semantics"), such as ballast water tanks inside ships, often present structured and repetitive spatial arrangements of the semantics of interest. Motivated by this, we first contribute an algorithm that identifies spatially repeating patterns of semantics - exact or inexact - in a semantic scene graph representation and makes predictions about the evolution of the graph in the unseen parts of the environment using these patterns. Furthermore, two inspection path planning strategies, tailored to ballast water tank inspection, that exploit these predictions are proposed. To assess the performance of the novel predictive planning paradigm, both simulation and experimental evaluations are performed. First, we conduct a simulation study comparing the method against relevant state-of-the-art techniques and further present tests showing its ability to handle imperfect patterns. Second, we deploy our method onboard a collision-tolerant aerial robot operating inside the ballast tanks of two real ships. The results, both in simulation and field experiments, demonstrate significant improvement over the state-of-the-art in terms of inspection time while maintaining equal or better semantic surface coverage. A set of videos describing the different parts of the method and the field deployments is available at https://tinyurl.com/spp-videos. The code for this work is made available at https://github.com/ntnu-arl/predictive_planning_ros.

cs.RO↗

arXiv2025

Unified Attention Modeling for Efficient Free-Viewing and Visual Search via Shared Representations

Computational human attention modeling in free-viewing and task-specific settings is often studied separately, with limited exploration of whether a common representation exists between them. This work investigates this question and proposes a neural network architecture that builds upon the Human Attention transformer (HAT) to test the hypothesis. Our results demonstrate that free-viewing and visual search can efficiently share a common representation, allowing a model trained in free-viewing attention to transfer its knowledge to task-driven visual search with a performance drop of only 3.86% in the predicted fixation scanpaths, measured by the semantic sequence score (SemSS) metric which reflects the similarity between predicted and human scanpaths. This transfer reduces computational costs by 92.29% in terms of GFLOPs and 31.23% in terms of trainable parameters.

cs.CV↗

arXiv2025

Semantically-driven Deep Reinforcement Learning for Inspection Path Planning

This paper introduces a novel semantics-aware inspection planning policy derived through deep reinforcement learning. Reflecting the fact that within autonomous informative path planning missions in unknown environments, it is often only a sparse set of objects of interest that need to be inspected, the method contributes an end-to-end policy that simultaneously performs semantic object visual inspection combined with collision-free navigation. Assuming access only to the instantaneous depth map, the associated segmentation image, the ego-centric local occupancy, and the history of past positions in the robot's neighborhood, the method demonstrates robust generalizability and successful crossing of the sim2real gap. Beyond simulations and extensive comparison studies, the approach is verified in experimental evaluations onboard a flying robot deployed in novel environments with previously unseen semantics and overall geometric configurations.

cs.RO↗