Cesar Cadena

Last Name

Cadena

First Name

Cesar

ORCID

0000-0002-2972-6011

Organisational unit

09570 - Hutter, Marco / Hutter, Marco

Show all metadata

Search Results

Publications1 - 10 of 73

Where Should I Walk? Predicting Terrain Properties from Images via Self-Supervised Learning
Wellhausen, Lorenz; Dosovitskiy, Alexey; Ranftl, René; et al. (2019)
IEEE Robotics and Automation Letters
Legged robots have the potential to traverse diverse and rugged terrain. To find a safe and efficient navigation path and to carefully select individual footholds, it is useful to be able to predict properties of the terrain ahead of the robot. In this work, we propose a method to collect data from robot-terrain interaction and associate it to images. Using sparse data acquired in teleoperation experiments with a quadrupedal robot,we train a neural network to generate a dense prediction of the terrain properties in front of the robot. To generate training data, we project the foothold positions from the robot trajectory into on-board camera images. We then attach labels to these footholds by identifying the dominant features of the force-torque signal measured with sensorized feet. We show that data collected in this fashion can be used to train a convolutional network for terrain property prediction as well as weakly supervised semantic segmentation. Finally, we show that the predicted terrain properties can be used for autonomous navigation of the ANYmal quadruped robot.
Temporal- and Viewpoint-Invariant Registration for Under-Canopy Footage using Deep-Learning-based Bird's-Eye View Prediction
Zhou, Jiawei; Mascaro, Ruben; Cadena, Cesar; et al. (2024)
2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Conducting visual assessments under the canopy using mobile robots is an emerging task in smart farming and forestry. However, it is challenging to register images across different data-collection days, especially across seasons, due to the self-occluding geometry and temporal dynamics in forests and orchards. This paper proposes a new approach for registering under-canopy image sequences in general and in these situations. Our methodology leverages standard GPS data and deep-learning-based perspective to bird’s-eye view conversion to provide an initial estimation of the positions of the trees in images and their association across datasets. Furthermore, it introduces an innovative strategy for extracting tree trunks and clean ground surfaces from noisy and sparse 3D reconstructions created from the image sequences, utilizing these features to achieve precise alignment. Our robust alignment method effectively mitigates position and scale drift, which may arise from GPS inaccuracies and Sparse Structure from Motion (SfM) limitations. We evaluate our approach on three challenging real-world datasets, demonstrating that our method outperforms ICP-based methods on average by 50%, and surpasses FGR and TEASER++ by over 90% in alignment accuracy. These results highlight our method’s cost efficiency and robustness, even in the presence of severe outliers and sparsity. https://github.com/VIS4ROBlab/bev_undercanopy_registration
Modular Sensor Fusion for Semantic Segmentation
Blum, Hermann; Gawel, Abel Roman; Siegwart, Roland; et al. (2018)
2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Sensor fusion is a fundamental process in robotic systems as it extends the perceptual range and increases robustness in real-world operations. Current multi-sensor deep learning based semantic segmentation approaches do not provide robustness to under-performing classes in one modality, or require a specific architecture with access to the full aligned multi-sensor training data. In this work, we analyze statistical fusion approaches for semantic segmentation that overcome these drawbacks while keeping a competitive performance. The studied approaches are modular by construction, allowing to have different training sets per modality and only a much smaller subset is needed to calibrate the statistical models. We evaluate a range of statistical fusion approaches and report their performance against state-of-the-art baselines on both realworld and simulated data. In our experiments, the approach improves performance in IoU over the best single modality segmentation results by up to 5%. We make all implementations and configurations publicly available.
Linewise Non-Rigid Point Cloud Registration
Castillón, Miguel; Ridao, Pere; Siegwart, Roland; et al. (2022)
IEEE Robotics and Automation Letters
Robots are usually equipped with 3D range sensors such as laser line scanners (LLSs) or lidars. These sensors acquire a full 3D scan in a line by line manner while the robot is in motion. All the lines can be referred to a common coordinate frame using data from inertial sensors. However, errors from noisy inertial measurements and inaccuracies in the extrinsic parameters between the scanner and the robot frame are also projected onto the shared frame. This causes a deformation in the final scan containing all the lines, which is known as motion distortion. Rigid point cloud registration with methods like ICP is therefore not well suited for such distorted scans. In this paper we present a non-rigid registration method that finds the rigid transformation to be applied to each line in the scan in order to match an existing model. We fully leverage the continuous and relatively smooth robot motion with respect to the scanning time to formulate our method reducing the computational complexity while improving accuracy. We use synthetic and real data to benchmark our method against a state-of-the-art non-rigid registration method. Finally, the source code for the algorithm is made publicly available.
A Unified Approach for Autonomous Volumetric Exploration of Large Scale Environments under Severe Odometry Drift
Schmid, Lukas; Reijgwart, Victor; Ott, Lionel; et al. (2021)
IEEE Robotics and Automation Letters
Exploration is a fundamental problem in robot autonomy. A major limitation, however, is that during exploration robots oftentimes have to rely on on-board systems alone for state estimation, accumulating significant drift over time in large environments. Drift can be detrimental to robot safety and exploration performance. In this work, a submap-based, multi-layer approach for both mapping and planning is proposed to enable safe and efficient volumetric exploration of large scale environments despite odometry drift. The central idea of our approach combines local (temporally and spatially) and global mapping to guarantee safety and efficiency. Similarly, our planning approach leverages the presented map to compute global volumetric frontiers in a changing global map and utilizes the nature of exploration dealing with partial information for efficient local and global planning. The presented system is thoroughly evaluated and shown to outperform state of the art methods even under drift-free conditions. Our system, termed GLocal , is made available open source.
Unsupervised Continual Semantic Adaptation Through Neural Rendering
Liu, Zhizheng; Milano, Francesco; Frey, Jonas; et al. (2023)
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
An increasing amount of applications rely on data-driven models that are deployed for perception tasks across a sequence of scenes. Due to the mismatch between training and deployment data, adapting the model on the new scenes is often crucial to obtain good performance. In this work, we study continual multi-scene adaptation for the task of semantic segmentation, assuming that no ground-truth labels are available during deployment and that performance on the previous scenes should be maintained. We propose training a Semantic-NeRF network for each scene by fusing the predictions of a segmentation model and then using the view-consistent rendered semantic labels as pseudo-labels to adapt the model. Through joint training with the segmentation model, the Semantic-NeRF model effectively enables 2D-3D knowledge transfer. Furthermore, due to its compact size, it can be stored in a long-term memory and subsequently used to render data from arbitrary viewpoints to reduce forgetting. We evaluate our approach on Scan-Net, where we outperform both a voxel-based baseline and a state-of-the-art unsupervised domain adaptation method.
Superquadric Object Representation for Optimization-based Semantic SLAM
Tschopp, Florian; Nieto, Juan; Siegwart, Roland; et al. (2021)
Introducing semantically meaningful objects to visual Simultaneous Localization and Mapping (SLAM) has the potential to improve both the accuracy and reliability of pose estimates, especially in challenging scenarios with significant viewpoint and appearance changes. However, how semantic objects should be represented for an efficient inclusion in optimization-based SLAM frameworks is still an open question. Superquadrics (SQs) are an efficient and compact object representation, able to represent most common object types to a high degree, and typically retrieved from 3D point-cloud data. However, accurate 3D point-cloud data might not be available in all applications. Recent advancements in machine learning enabled robust object recognition and semantic mask measurements from camera images under many different appearance conditions. We propose a pipeline to leverage such semantic mask measurements to fit SQ parameters to multi-view camera observations using a multi-stage initialization and optimization procedure. We demonstrate the system's ability to retrieve randomly generated SQ parameters from multi-view mask observations in preliminary simulation experiments and evaluate different initialization stages and cost functions.
Informed, Constrained, Aligned: A Field Analysis on Degeneracy-aware Point Cloud Registration in the Wild
Tuna, Turcan; Nubert, Julian; Pfreundschuh, Patrick; et al. (2025)
IEEE Transactions on Field Robotics
The iterative closest point (ICP) registration algorithm has been a preferred method for light detection and ranging (LiDAR)-based robot localization for nearly a decade. However, even in modern simultaneous localization and mapping (SLAM) solutions, ICP can degrade and become unreliable in geometrically ill-conditioned environments. Current solutions primarily focus on utilizing additional sources of information, such as external odometry, to either replace the degenerate directions of the optimization solution or add additional constraints in a sensor-fusion setup afterward. In response, this work investigates and compares new and existing degeneracy mitigation methods for robust LiDAR-based localization and analyzes the efficacy of these approaches in degenerate environments for the first time in the literature at this scale. Specifically, this work investigates i) the effect of using active or passive degeneracy mitigation methods for the problem of ill-conditioned ICP in LiDAR degenerate environments and ii) the evaluation of truncated singular value decomposition (TSVD), inequality constraints (Ineq. Con.), and linear/nonlinear Tikhonov regularization for the application of degenerate point cloud registration for the first time. Furthermore, a sensitivity analysis for the least-squares minimization step of the ICP problem is carried out to better understand how each method affects the optimization and what to expect from each method. The results of the analysis are validated through multiple real-world robotic field and simulated experiments. The analysis demonstrates that active optimization degeneracy mitigation is necessary and advantageous in the absence of reliable external estimate assistance for LiDAR-SLAM, and soft-constrained methods can provide better results in complex ill-conditioned scenarios with heuristic fine-tuned parameters. The code and data used in this work are made publicly available to the community.
MOZARD: Multi-Modal Localization for Autonomous Vehicles in Urban Outdoor Environments
Schaupp, Lukas; Pfreundschuh, Patrick; Bürki, Mathias; et al. (2020)
2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Visually poor scenarios are one of the main sources of failure in visual localization systems in outdoor environments. To address this challenge, we present MOZARD, a multi-modal localization system for urban outdoor environments using vision and LiDAR. By fusing key point based visual multi-session information with semantic data, an improved localization recall can be achieved across vastly different appearance conditions. In particular we focus on the use of curbstone information because of their broad distribution and reliability within urban environments. We present thorough experimental evaluations on several driving kilometers in challenging urban outdoor environments, analyze the recall and accuracy of our localization system and demonstrate in a case study possible failure cases of each subsystem. We demonstrate that MOZARD is able to bridge scenarios where our previous key point based visual approach, VIZARD, fails, hence yielding an increased recall performance, while a similar localization accuracy of 0.2m is achieved. © 2020 IEEE.
Team CERBERUS Wins the DARPA Subterranean Challenge: Technical Overview and Lessons Learned
Tranzatto, Marco; Dharmadhikari, Mihir; Bernreiter, Lukas; et al. (2024)
Field Robotics
This article presents the CERBERUS robotic system-of-systems, which won the DARPA Subterranean Challenge Final Event in 2021. The Subterranean Challenge was organized by DARPA with the vision to facilitate the novel technologies necessary to reliably explore diverse underground environments despite the grueling challenges they present for robotic autonomy. Due to their geometric complexity, degraded perceptual conditions combined with lack of GNSS support, austere navigation conditions, and denied communications, subterranean settings render autonomous operations particularly demanding. In response to this challenge, we developed the CERBERUS system which exploits the synergy of legged and flying robots, coupled with robust control especially for overcoming perilous terrain, multi-modal and multi-robot perception for localization and mapping in conditions of sensor degradation, and resilient autonomy through unified exploration path planning and local motion planning that reflects robot-specific limitations. Based on its ability to explore diverse underground environments and its high-level command and control by a single human supervisor, CERBERUS demonstrated efficient exploration, reliable detection of objects of interest, and accurate mapping. In this article, we report results from both the preliminary runs and the final Prize Round of the DARPA Subterranean Challenge, and discuss highlights and challenges faced, alongside lessons learned for the benefit of the community.

Publications1 - 10 of 73

Cesar Cadena

Last Name

First Name

ORCID

Organisational unit

Filters

Search Results