Search

We demonstrate the advantages of THz frequency combs for high-resolution spectroscopy. This benefits from wide spectral coverage and the exact knowledge of the frequency position of each comb component. Heterodyne detection combined with a fast Fourier spectrometer enables rapid and simultaneous measurement of more than 80 frequency comb modes covering a 7.5 GHz bandwidth. A spectrum is obtained in under 20 minutes yielding a uniform resolution of 70 kHz. This new setup has been validated by recording more than 150 lines of methanol around 723 GHz, and represents a new solution to exploit THz frequency combs for high-resolution spectroscopy.

High resolution rotational Terahertz (THz) spectroscopy has been widely applied to the studies of numerous polar gas phase molecules, in particular volatile organic compounds (VOCs). During the storage of foodstuffs packed under a protective atmosphere, microbial activity will lead to the generation of a complex mixture of trace gases that could be used as food spoilage indicators. Here we have demonstrated that the THz instrumentation presently available provides sufficient sensitivity and selectivity to monitor the generation of hydrogen sulfide (H2S) in the headspace of packed Atlantic salmon (Salmo salar) fillet portions. A comprehensive comparison was made by selective-ion flow-tube mass spectrometry (SIFT-MS) in order to validate the THz measurements and protocol. The detectivity of a range of alternative compounds for this application is also provided, based on the experimental detection limit observed and molecular spectroscopic properties. Molecules like ethanol, methyl mercaptan and ammonia are suitable indicators with the presently available sensitivity levels, while dimethyl sulfide, acetone and butanone may be considered with a sensitivity improvement of 2 orders of magnitude.

Air ducts are integral to modern buildings but are challenging to access for inspection. Small quadrotor drones offer a potential solution, as they can navigate both horizontal and vertical sections and smoothly fly over debris. However, hovering inside air ducts is problematic due to the airflow generated by the rotors, which recirculates inside the duct and destabilizes the drone, whereas hovering is a key feature for many inspection missions. In this article, we map the aerodynamic forces that affect a hovering drone in a duct using a robotic setup and a force/torque sensor. Based on the collected aerodynamic data, we identify a recommended position for stable flight, which corresponds to the bottom third for a circular duct. We then develop a neural network-based positioning system that leverages low-cost time-of-flight sensors. By combining these aerodynamic insights and the data-driven positioning system, we show that a small quadrotor drone (here, 180 mm) can hover and fly inside small air ducts, starting with a diameter of 350 mm. These results open a new and promising application domain for drones., Comment: Video: https://youtu.be/BLQqoa7Zolw

This paper investigates tree species classification using Sentinel-2 multispectral satellite image time-series. Despite their critical importance for many applications, such maps are often unavailable, outdated, or inaccurate for large areas. The interest of using remote sensing time series to produce these maps has been highlighted in many studies. However, many methods proposed in the literature still rely on a standard classification algorithm, usually the Random Forest (RF) algorithm with vegetation indices. This study shows that the use of deep learning models can lead to a significant improvement in classification results, especially in an imbalanced context where the RF algorithm tends to predict towards the majority class. In our use case in the center of France with 10 tree species, we obtain an overall accuracy (OA) around 95% and a F1-macro score around 80% using three different benchmark deep learning architectures. In contrast, using the RF algorithm yields an OA of 93% and an F1 of 60%, indicating that the minority classes are not classified with sufficient accuracy. Therefore, the proposed framework is a strong baseline that can be easily implemented in most scenarios, even with a limited amount of reference data. Our results highlight that standard multilayer perceptron can be competitive with batch normalization and a sufficient amount of parameters. Other architectures (convolutional or attention-based) can also achieve strong results when tuned properly. Furthermore, our results show that DL models are naturally robust to imbalanced data, although similar results can be obtained using dedicated techniques.

This paper presents Words2Contact, a language-guided multi-contact placement pipeline leveraging large language models and vision language models. Our method is a key component for language-assisted teleoperation and human-robot cooperation, where human operators can instruct the robots where to place their support contacts before whole-body reaching or manipulation using natural language. Words2Contact transforms the verbal instructions of a human operator into contact placement predictions; it also deals with iterative corrections, until the human is satisfied with the contact location identified in the robot's field of view. We benchmark state-of-the-art LLMs and VLMs for size and performance in contact prediction. We demonstrate the effectiveness of the iterative correction process, showing that users, even naive, quickly learn how to instruct the system to obtain accurate locations. Finally, we validate Words2Contact in real-world experiments with the Talos humanoid robot, instructed by human operators to place support contacts on different locations and surfaces to avoid falling when reaching for distant objects.

Humanoid robots could benefit from using their upper bodies for support contacts, enhancing their workspace, stability, and ability to perform contact-rich and pushing tasks. In this paper, we propose a unified approach that combines an optimization-based multi-contact whole-body controller with Flow Matching, a recently introduced method capable of generating multi-modal trajectory distributions for imitation learning. In simulation, we show that Flow Matching is more appropriate for robotics than Diffusion and traditional behavior cloning. On a real full-size humanoid robot (Talos), we demonstrate that our approach can learn a whole-body non-prehensile box-pushing task and that the robot can close dishwasher drawers by adding contacts with its free hand when needed for balance. We also introduce a shared autonomy mode for assisted teleoperation, providing automatic contact placement for tasks not covered in the demonstrations. Full experimental videos are available at: https://hucebot.github.io/flow_multisupport_website/, Comment: 2024 IEEE-RAS 23rd International Conference on Humanoid Robots (Humanoids), Nov 2024, Nancy, France

Optimizing a set of functions simultaneously by leveraging their similarity is called multi-task optimization. Current black-box multi-task algorithms only solve a finite set of tasks, even when the tasks originate from a continuous space. In this paper, we introduce Parametric-Task MAP-Elites (PT-ME), a new black-box algorithm for continuous multi-task optimization problems. This algorithm (1) solves a new task at each iteration, effectively covering the continuous space, and (2) exploits a new variation operator based on local linear regression. The resulting dataset of solutions makes it possible to create a function that maps any task parameter to its optimal solution. We show that PT-ME outperforms all baselines, including the deep reinforcement learning algorithm PPO on two parametric-task toy problems and a robotic problem in simulation.

Many humanoid and multi-legged robots are controlled in positions rather than in torques, which prevents direct control of contact forces, and hampers their ability to create multiple contacts to enhance their balance, such as placing a hand on a wall or a handrail. This letter introduces the SEIKO (Sequential Equilibrium Inverse Kinematic Optimization) pipeline, and proposes a unified formulation that exploits an explicit model of flexibility to indirectly control contact forces on traditional position-controlled robots. SEIKO formulates whole-body retargeting from Cartesian commands and admittance control using two quadratic programs solved in real-time. Our pipeline is validated with experiments on the real, full-scale humanoid robot Talos in various multi-contact scenarios, including pushing tasks, far-reaching tasks, stair climbing, and stepping on sloped surfaces. Code and videos are available at: https://hucebot.github.io/seiko_controller_website/

Mapping forest resources and carbon is important for improving forest management and meeting the objectives of storing carbon and preserving the environment. Spaceborne remote sensing approaches have considerable potential to support forest height monitoring by providing repeated observations at high spatial resolution over large areas. This study uses a machine learning approach that was previously developed to produce local maps of forest parameters (basal area, height, diameter, etc.). The aim of this paper is to present the extension of the approach to much larger scales such as the French national coverage. We used the GEDI Lidar mission as reference height data, and the satellite images from Sentinel-1, Sentinel-2 and ALOS-2 PALSA-2 to estimate forest height and produce a map of France for the year 2020. The height map is then derived into volume and aboveground biomass (AGB) using allometric equations. The validation of the height map with local maps from ALS data shows an accuracy close to the state of the art, with a mean absolute error (MAE) of 4.3 m. Validation on inventory plots representative of French forests shows an MAE of 3.7 m for the height. Estimates are slightly better for coniferous than for broadleaved forests. Volume and AGB maps derived from height shows MAEs of 75 tons/ha and 93 m${}^3$/ha respectively. The results aggregated by sylvo-ecoregion and forest types (owner and species) are further improved, with MAEs of 23 tons/ha and 30 m${}^3$/ha. The precision of these maps allows to monitor forests locally, as well as helping to analyze forest resources and carbon on a territorial scale or on specific types of forests by combining the maps with geolocated information (administrative area, species, type of owner, protected areas, environmental conditions, etc.). Height, volume and AGB maps produced in this study are made freely available.

This short paper outlines two recent works on multi-contact teleoperation and the development of the SEIKO (Sequential Equilibrium Inverse Kinematic Optimization) framework. SEIKO adapts commands from the operator in real-time and ensures that the reference configuration sent to the underlying controller is feasible. Additionally, an admittance scheme is used to implement physical interaction, which is then combined with the operator's command and retargeted. SEIKO has been applied in simulations on various robots, including humanoid and quadruped robots designed for loco-manipulation. Furthermore, SEIKO has been tested on real hardware for bimanual heavy object carrying tasks., Comment: 2nd Workshop Toward Robot Avatars, 2023 IEEE International Conference on Robotics and Automation (ICRA), Jun 2023, London, United Kingdom

Quality Diversity (QD) algorithms such as MAP-Elites are a class of optimisation techniques that attempt to find many high performing points that all behave differently according to a user-defined behavioural metric. In this paper we propose the Bayesian Optimisation of Elites (BOP-Elites) algorithm. Designed for problems with expensive black-box fitness and behaviour functions, it is able to return a QD solution-set with excellent final performance already after a relatively small number of samples. BOP-Elites models both fitness and behavioural descriptors with Gaussian Process (GP) surrogate models and uses Bayesian Optimisation (BO) strategies for choosing points to evaluate in order to solve the quality-diversity problem. In addition, BOP-Elites produces high quality surrogate models which can be used after convergence to predict solutions with any behaviour in a continuous range. An empirical comparison shows that BOP-Elites significantly outperforms other state-of-the-art algorithms without the need for problem-specific parameter tuning.

We propose Multi-Task Multi-Behavior MAP-Elites, a variant of MAP-Elites that finds a large number of high-quality solutions for a large set of tasks (optimization problems from a given family). It combines the original MAP-Elites for the search for diversity and Multi-Task MAP-Elites for leveraging similarity between tasks. It performs better than three baselines on a humanoid fault-recovery set of tasks, solving more tasks and finding twice as many solutions per solved task., Comment: Accepted as Poster for GECCO 2023

Humanoid robots could replace humans in hazardous situations but most of such situations are equally dangerous for them, which means that they have a high chance of being damaged and falling. We hypothesize that humanoid robots would be mostly used in buildings, which makes them likely to be close to a wall. To avoid a fall, they can therefore lean on the closest wall, as a human would do, provided that they find in a few milliseconds where to put the hand(s). This article introduces a method, called D-Reflex, that learns a neural network that chooses this contact position given the wall orientation, the wall distance, and the posture of the robot. This contact position is then used by a whole-body controller to reach a stable posture. We show that D-Reflex allows a simulated TALOS robot (1.75m, 100kg, 30 degrees of freedom) to avoid more than 75% of the avoidable falls and can work on the real robot., Comment: Accepted in IEEE Robotics and Automation Letters, June, 2022 Video presenting the results: https://youtu.be/hbuWr-ZNAtg

Grasping made impressive progress during the last few years thanks to deep learning. However, there are many objects for which it is not possible to choose a grasp by only looking at an RGB-D image, might it be for physical reasons (e.g., a hammer with uneven mass distribution) or task constraints (e.g., food that should not be spoiled). In such situations, the preferences of experts need to be taken into account. In this paper, we introduce a data-efficient grasping pipeline (Latent Space GP Selector -- LGPS) that learns grasp preferences with only a few labels per object (typically 1 to 4) and generalizes to new views of this object. Our pipeline is based on learning a latent space of grasps with a dataset generated with any state-of-the-art grasp generator (e.g., Dex-Net). This latent space is then used as a low-dimensional input for a Gaussian process classifier that selects the preferred grasp among those proposed by the generator. The results show that our method outperforms both GR-ConvNet and GG-CNN (two state-of-the-art methods that are also based on labeled grasps) on the Cornell dataset, especially when only a few labels are used: only 80 labels are enough to correctly choose 80% of the grasps (885 scenes, 244 objects). Results are similar on our dataset (91 scenes, 28 objects)., Comment: Video: https://youtu.be/dJ1fkcught4

This paper tackles the problem of missing data imputation for noisy and non-Gaussian data. A classical imputation method, the Expectation Maximization (EM) algorithm for Gaussian mixture models, has shown interesting properties when compared to other popular approaches such as those based on k-nearest neighbors or on multiple imputations by chained equations. However, Gaussian mixture models are known to be non-robust to heterogeneous data, which can lead to poor estimation performance when the data is contaminated by outliers or follows non-Gaussian distributions. To overcome this issue, a new EM algorithm is investigated for mixtures of elliptical distributions with the property of handling potential missing data. This paper shows that this problem reduces to the estimation of a mixture of Angular Gaussian distributions under generic assumptions (i.e., each sample is drawn from a mixture of elliptical distributions, which is possibly different for one sample to another). In that case, the complete-data likelihood associated with mixtures of elliptical distributions is well adapted to the EM framework with missing data thanks to its conditional distribution, which is shown to be a multivariate $t$-distribution. Experimental results on synthetic data demonstrate that the proposed algorithm is robust to outliers and can be used with non-Gaussian data. Furthermore, experiments conducted on real-world datasets show that this algorithm is very competitive when compared to other classical imputation methods.

Reinforcement learning agents perform well when presented with inputs within the distribution of those encountered during training. However, they are unable to respond effectively when faced with novel, out-of-distribution events, until they have undergone additional training. This paper presents an online, data-driven, emergency-response method that aims to provide autonomous agents the ability to react to unexpected situations that are very different from those it has been trained or designed to address. In such situations, learned policies cannot be expected to perform appropriately since the observations obtained in these novel situations would fall outside the distribution of inputs that the agent has been optimized to handle. The proposed approach devises a customized response to the unforeseen situation sequentially, by selecting actions that minimize the rate of increase of the reconstruction error from a variational auto-encoder. This optimization is achieved online in a data-efficient manner (on the order of 30 data-points) using a modified Bayesian optimization procedure. We demonstrate the potential of this approach in a simulated 3D car driving scenario, in which the agent devises a response in under 2 seconds to avoid collisions with objects it has not seen during training.

Missing data is a recurrent problem in remote sensing, mainly due to cloud coverage for multispectral images and acquisition problems. This can be a critical issue for crop monitoring, especially for applications relying on machine learning techniques, which generally assume that the feature matrix does not have missing values. This paper proposes a Gaussian Mixture Model (GMM) for the reconstruction of parcel-level features extracted from multispectral images. A robust version of the GMM is also investigated, since datasets can be contaminated by inaccurate samples or features (e.g., wrong crop type reported, inaccurate boundaries, undetected clouds, etc). Additional features extracted from Synthetic Aperture Radar (SAR) images using Sentinel-1 data are also used to provide complementary information and improve the imputations. The robust GMM investigated in this work assigns reduced weights to the outliers during the estimation of the GMM parameters, which improves the final reconstruction. These weights are computed at each step of an Expectation-Maximization (EM) algorithm by using outlier scores provided by the isolation forest algorithm. Experimental validation is conducted on rapeseed and wheat parcels located in the Beauce region (France). Overall, we show that the GMM imputation method outperforms other reconstruction strategies. A mean absolute error (MAE) of 0.013 (resp. 0.019) is obtained for the imputation of the median Normalized Difference Index (NDVI) of the rapeseed (resp. wheat) parcels. Other indicators (e.g., Normalized Difference Water Index) and statistics (for instance the interquartile range, which captures heterogeneity among the parcel indicator) are reconstructed at the same time with good accuracy. In a dataset contaminated by irrelevant samples, using the robust GMM is recommended since the standard GMM imputation can lead to inaccurate imputed values.

Visual prediction models are a promising solution for visual-based robotic grasping of cluttered, unknown soft objects. Previous models from the literature are computationally greedy, which limits reproducibility; although some consider stochasticity in the prediction model, it is often too weak to catch the reality of robotics experiments involving grasping such objects. Furthermore, previous work focused on elementary movements that are not efficient to reason in terms of more complex semantic actions. To address these limitations, we propose VP-GO, a ``light'' stochastic action-conditioned visual prediction model. We propose a hierarchical decomposition of semantic grasping and manipulation actions into elementary end-effector movements, to ensure compatibility with existing models and datasets for visual prediction of robotic actions such as RoboNet. We also record and release a new open dataset for visual prediction of object grasping, called PandaGrasp. Our model can be pre-trained on RoboNet and fine-tuned on PandaGrasp, and performs similarly to more complex models in terms of signal prediction metrics. Qualitatively, it outperforms when predicting the outcome of complex grasps performed by our robot.

Humanoid robots could be versatile and intuitive human avatars that operate remotely in inaccessible places: the robot could reproduce in the remote location the movements of an operator equipped with a wearable motion capture device while sending visual feedback to the operator. While substantial progress has been made on transferring ("retargeting") human motions to humanoid robots, a major problem preventing the deployment of such systems in real applications is the presence of communication delays between the human input and the feedback from the robot: even a few hundred milliseconds of delay can irreversibly disturb the operator, let alone a few seconds. To overcome these delays, we introduce a system in which a humanoid robot executes commands before it actually receives them, so that the visual feedback appears to be synchronized to the operator, whereas the robot executed the commands in the past. To do so, the robot continuously predicts future commands by querying a machine learning model that is trained on past trajectories and conditioned on the last received commands. In our experiments, an operator was able to successfully control a humanoid robot (32 degrees of freedom) with stochastic delays up to 2 seconds in several whole-body manipulation tasks, including reaching different targets, picking up a bottle, and placing a box at distinct locations., Comment: Video: https://www.youtube.com/watch?v=N3u4ot3aIyQ