Fast Online Learning of CLiFF-maps in Changing Environments

Maps of dynamics are effective representations of motion patterns learned from prior observations, with recent research demonstrating their ability to enhance performance in various downstream tasks such as human-aware robot navigation, long-term human motion prediction, and robot localization. Current advancements have primarily concentrated on methods for learning maps of human flow in environments where the flow is static, i.e., not assumed to change over time. In this paper we propose a method to update the CLiFF-map, one type of map of dynamics, for achieving efficient life-long robot operation. As new observations are collected, our goal is to update a CLiFF-map to effectively and accurately integrate new observations, while retaining relevant historic motion patterns. The proposed online update method maintains a probabilistic representation in each observed location, updating parameters by continuously tracking sufficient statistics. In experiments using both synthetic and real-world datasets, we show that our method is able to maintain accurate representations of human motion dynamics, contributing to high performance flow-compliant planning downstream tasks, while being orders of magnitude faster than the comparable baselines.

Human Gaze and Head Rotation during Navigation, Exploration and Object Manipulation in Shared Environments with Robots

The human gaze is an important cue to signal intention, attention, distraction, and the regions of interest in the immediate surroundings. Gaze tracking can transform how robots perceive, understand, and react to people, enabling new modes of robot control, interaction, and collaboration. In this paper, we use gaze tracking data from a rich dataset of human motion (TH\"OR-MAGNI) to investigate the coordination between gaze direction and head rotation of humans engaged in various indoor activities involving navigation, interaction with objects, and collaboration with a mobile robot. In particular, we study the spread and central bias of fixations in diverse activities and examine the correlation between gaze direction and head rotation. We introduce various human motion metrics to enhance the understanding of gaze behavior in dynamic interactions. Finally, we apply semantic object labeling to decompose the gaze distribution into activity-relevant regions.

Human Detection from 4D Radar Data in Low-Visibility Field Conditions

Autonomous driving technology is increasingly being used on public roads and in industrial settings such as mines. While it is essential to detect pedestrians, vehicles, or other obstacles, adverse field conditions negatively affect the performance of classical sensors such as cameras or lidars. Radar, on the other hand, is a promising modality that is less affected by, e.g., dust, smoke, water mist or fog. In particular, modern 4D imaging radars provide target responses across the range, vertical angle, horizontal angle and Doppler velocity dimensions. We propose TMVA4D, a CNN architecture that leverages this 4D radar modality for semantic segmentation. The CNN is trained to distinguish between the background and person classes based on a series of 2D projections of the 4D radar data that include the elevation, azimuth, range, and Doppler velocity dimensions. We also outline the process of compiling a novel dataset consisting of data collected in industrial settings with a car-mounted 4D radar and describe how the ground-truth labels were generated from reference thermal images. Using TMVA4D on this dataset, we achieve an mIoU score of 78.2% and an mDice score of 86.1%, evaluated on the two classes background and person

LaCE-LHMP: Airflow Modelling-Inspired Long-Term Human Motion Prediction By Enhancing Laminar Characteristics in Human Flow

Long-term human motion prediction (LHMP) is essential for safely operating autonomous robots and vehicles in populated environments. It is fundamental for various applications, including motion planning, tracking, human-robot interaction and safety monitoring. However, accurate prediction of human trajectories is challenging due to complex factors, including, for example, social norms and environmental conditions. The influence of such factors can be captured through Maps of Dynamics (MoDs), which encode spatial motion patterns learned from (possibly scattered and partial) past observations of motion in the environment and which can be used for data-efficient, interpretable motion prediction (MoD-LHMP). To address the limitations of prior work, especially regarding accuracy and sensitivity to anomalies in long-term prediction, we propose the Laminar Component Enhanced LHMP approach (LaCE-LHMP). Our approach is inspired by data-driven airflow modelling, which estimates laminar and turbulent flow components and uses predominantly the laminar components to make flow predictions. Based on the hypothesis that human trajectory patterns also manifest laminar flow (that represents predictable motion) and turbulent flow components (that reflect more unpredictable and arbitrary motion), LaCE-LHMP extracts the laminar patterns in human dynamics and uses them for human motion prediction. We demonstrate the superior prediction performance of LaCE-LHMP through benchmark comparisons with state-of-the-art LHMP methods, offering an unconventional perspective and a more intuitive understanding of human movement patterns.

High-Fidelity SLAM Using Gaussian Splatting with Rendering-Guided Densification and Regularized Optimization

We propose a dense RGBD SLAM system based on 3D Gaussian Splatting that provides metrically accurate pose tracking and visually realistic reconstruction. To this end, we first propose a Gaussian densification strategy based on the rendering loss to map unobserved areas and refine reobserved areas. Second, we introduce extra regularization parameters to alleviate the forgetting problem in the continuous mapping problem, where parameters tend to overfit the latest frame and result in decreasing rendering quality for previous frames. Both mapping and tracking are performed with Gaussian parameters by minimizing re-rendering loss in a differentiable way. Compared to recent neural and concurrently developed gaussian splatting RGBD SLAM baselines, our method achieves state-of-the-art results on the synthetic dataset Replica and competitive results on the real-world dataset TUM.

THÖR-MAGNI: A Large-scale Indoor Motion Capture Recording of Human Movement and Robot Interaction

We present a new large dataset of indoor human and robot navigation and interaction, called TH\"OR-MAGNI, that is designed to facilitate research on social navigation: e.g., modelling and predicting human motion, analyzing goal-oriented interactions between humans and robots, and investigating visual attention in a social interaction context. TH\"OR-MAGNI was created to fill a gap in available datasets for human motion analysis and HRI. This gap is characterized by a lack of comprehensive inclusion of exogenous factors and essential target agent cues, which hinders the development of robust models capable of capturing the relationship between contextual cues and human behavior in different scenarios. Unlike existing datasets, TH\"OR-MAGNI includes a broader set of contextual features and offers multiple scenario variations to facilitate factor isolation. The dataset includes many social human-human and human-robot interaction scenarios, rich context annotations, and multi-modal data, such as walking trajectories, gaze tracking data, and lidar and camera streams recorded from a mobile robot. We also provide a set of tools for visualization and processing of the recorded data. TH\"OR-MAGNI is, to the best of our knowledge, unique in the amount and diversity of sensor data collected in a contextualized and socially dynamic environment, capturing natural human-robot interactions.

3QFP: Efficient neural implicit surface reconstruction using Tri-Quadtrees and Fourier feature Positional encoding

Neural implicit surface representations are currently receiving a lot of interest as a means to achieve high-fidelity surface reconstruction at a low memory cost, compared to traditional explicit representations.However, state-of-the-art methods still struggle with excessive memory usage and non-smooth surfaces. This is particularly problematic in large-scale applications with sparse inputs, as is common in robotics use cases. To address these issues, we first introduce a sparse structure, \emph{tri-quadtrees}, which represents the environment using learnable features stored in three planar quadtree projections. Secondly, we concatenate the learnable features with a Fourier feature positional encoding. The combined features are then decoded into signed distance values through a small multi-layer perceptron. We demonstrate that this approach facilitates smoother reconstruction with a higher completion ratio with fewer holes. Compared to two recent baselines, one implicit and one explicit, our approach requires only 10\%--50\% as much memory, while achieving competitive quality.

Learning Extrinsic Dexterity with Parameterized Manipulation Primitives

Many practically relevant robot grasping problems feature a target object for which all grasps are occluded, e.g., by the environment. Single-shot grasp planning invariably fails in such scenarios. Instead, it is necessary to first manipulate the object into a configuration that affords a grasp. We solve this problem by learning a sequence of actions that utilize the environment to change the object's pose. Concretely, we employ hierarchical reinforcement learning to combine a sequence of learned parameterized manipulation primitives. By learning the low-level manipulation policies, our approach can control the object's state through exploiting interactions between the object, the gripper, and the environment. Designing such a complex behavior analytically would be infeasible under uncontrolled conditions, as an analytic approach requires accurate physical modeling of the interaction and contact dynamics. In contrast, we learn a hierarchical policy model that operates directly on depth perception data, without the need for object detection, pose estimation, or manual design of controllers. We evaluate our approach on picking box-shaped objects of various weight, shape, and friction properties from a constrained table-top workspace. Our method transfers to a real robot and is able to successfully complete the object picking task in 98\% of experimental trials.

Do we need scan-matching in radar odometry?

There is a current increase in the development of "4D" Doppler-capable radar and lidar range sensors that produce 3D point clouds where all points also have information about the radial velocity relative to the sensor. 4D radars in particular are interesting for object perception and navigation in low-visibility conditions (dust, smoke) where lidars and cameras typically fail. With the advent of high-resolution Doppler-capable radars comes the possibility of estimating odometry from single point clouds, foregoing the need for scan registration which is error-prone in feature-sparse field environments. We compare several odometry estimation methods, from direct integration of Doppler/IMU data and Kalman filter sensor fusion to 3D scan-to-scan and scan-to-map registration, on three datasets with data from two recent 4D radars and two IMUs. Surprisingly, our results show that the odometry from Doppler and IMU data alone give similar or better results than 3D point cloud registration. In our experiments, the average position error can be as low as 0.3% over 1.8 and 4.5km trajectories. That allows accurate estimation of 6DOF ego-motion over long distances also in feature-sparse mine environments. These results are useful not least for applications of navigation with resource-constrained robot platforms in feature-sparse and low-visibility conditions such as mining, construction, and search & rescue operations.

Doppler-only Single-scan 3D Vehicle Odometry

We present a novel 3D odometry method that recovers the full motion of a vehicle only from a Doppler-capable range sensor. It leverages the radial velocities measured from the scene, estimating the sensor's velocity from a single scan. The vehicle's 3D motion, defined by its linear and angular velocities, is calculated taking into consideration its kinematic model which provides a constraint between the velocity measured at the sensor frame and the vehicle frame. Experiments carried out prove the viability of our single-sensor method compared to mounting an additional IMU. Our method provides the translation of the sensor, which cannot be reliably determined from an IMU, as well as its rotation. Its short-term accuracy and fast operation (~5ms) make it a proper candidate to supply the initialization to more complex localization algorithms or mapping pipelines. Not only does it reduce the error of the mapper, but it does so at a comparable level of accuracy as an IMU would. All without the need to mount and calibrate an extra sensor on the vehicle.