Volumetric Instance-Aware Semantic Mapping and 3D Object Discovery

To autonomously navigate and plan interactions in real-world environments, robots require the ability to robustly perceive and map complex, unstructured surrounding scenes. Besides building an internal representation of the observed scene geometry, the key insight towards a truly functional understanding of the environment is the usage of higher-level entities during mapping, such as individual object instances. We propose an approach to incrementally build volumetric object-centric maps during online scanning with a localized RGB-D camera. First, a per-frame segmentation scheme combines an unsupervised geometric approach with instance-aware semantic object predictions. This allows us to detect and segment elements both from the set of known classes and from other, previously unseen categories. Next, a data association step tracks the predicted instances across the different frames. Finally, a map integration strategy fuses information about their 3D shape, location, and, if available, semantic class into a global volume. Evaluation on a publicly available dataset shows that the proposed approach for building instance-level semantic maps is competitive with state-of-the-art methods, while additionally able to discover objects of unseen categories. The system is further evaluated within a real-world robotic mapping setup, for which qualitative results highlight the online nature of the method.

VIZARD: Reliable Visual Localization for Autonomous Vehicles in Urban Outdoor Environments

Changes in appearance is one of the main sources of failure in visual localization systems in outdoor environments. To address this challenge, we present VIZARD, a visual localization system for urban outdoor environments. By combining a local localization algorithm with the use of multi-session maps, a high localization recall can be achieved across vastly different appearance conditions. The fusion of the visual localization constraints with wheel-odometry in a state estimation framework further guarantees smooth and accurate pose estimates. In an extensive experimental evaluation on several hundreds of driving kilometers in challenging urban outdoor environments, we analyze the recall and accuracy of our localization system, investigate its key parameters and boundary conditions, and compare different types of feature descriptors. Our results show that VIZARD is able to achieve nearly 100% recall with a localization accuracy below 0.5m under varying outdoor appearance conditions, including at night-time.

Observability-aware Self-Calibration of Visual and Inertial Sensors for Ego-Motion Estimation

External effects such as shocks and temperature variations affect the calibration of visual-inertial sensor systems and thus they cannot fully rely on factory calibrations. Re-calibrations performed on short user-collected datasets might yield poor performance since the observability of certain parameters is highly dependent on the motion. Additionally, on resource-constrained systems (e.g mobile phones), full-batch approaches over longer sessions quickly become prohibitively expensive. In this paper, we approach the self-calibration problem by introducing information theoretic metrics to assess the information content of trajectory segments, thus allowing to select the most informative parts from a dataset for calibration purposes. With this approach, we are able to build compact calibration datasets either: (a) by selecting segments from a long session with limited exciting motion or (b) from multiple short sessions where a single sessions does not necessarily excite all modes sufficiently. Real-world experiments in four different environments show that the proposed method achieves comparable performance to a batch calibration approach, yet, at a constant computational complexity which is independent of the duration of the session.

SegMatch: Segment based loop-closure for 3D point clouds

Loop-closure detection on 3D data is a challenging task that has been commonly approached by adapting image-based solutions. Methods based on local features suffer from ambiguity and from robustness to environment changes while methods based on global features are viewpoint dependent. We propose SegMatch, a reliable loop-closure detection algorithm based on the matching of 3D segments. Segments provide a good compromise between local and global descriptions, incorporating their strengths while reducing their individual drawbacks. SegMatch does not rely on assumptions of "perfect segmentation", or on the existence of "objects" in the environment, which allows for reliable execution on large scale, unstructured environments. We quantitatively demonstrate that SegMatch can achieve accurate localization at a frequency of 1Hz on the largest sequence of the KITTI odometry dataset. We furthermore show how this algorithm can reliably detect and close loops in real-time, during online operation. In addition, the source code for the SegMatch algorithm will be made available after publication.

SegMap: 3D Segment Mapping using Data-Driven Descriptors

When performing localization and mapping, working at the level of structure can be advantageous in terms of robustness to environmental changes and differences in illumination. This paper presents SegMap: a map representation solution to the localization and mapping problem based on the extraction of segments in 3D point clouds. In addition to facilitating the computationally intensive task of processing 3D point clouds, working at the level of segments addresses the data compression requirements of real-time single- and multi-robot systems. While current methods extract descriptors for the single task of localization, SegMap leverages a data-driven descriptor in order to extract meaningful features that can also be used for reconstructing a dense 3D map of the environment and for extracting semantic information. This is particularly interesting for navigation tasks and for providing visual feedback to end-users such as robot operators, for example in search and rescue scenarios. These capabilities are demonstrated in multiple urban driving and search and rescue experiments. Our method leads to an increase of area under the ROC curve of 28.3% over current state of the art using eigenvalue based features. We also obtain very similar reconstruction capabilities to a model specifically trained for this task. The SegMap implementation will be made available open-source along with easy to run demonstrations at www.github.com/ethz-asl/segmap. A video demonstration is available at https://youtu.be/CMk4w4eRobg.

From Coarse to Fine: Robust Hierarchical Localization at Large Scale

Robust and accurate visual localization is a fundamental capability for numerous applications, such as autonomous driving, mobile robotics, or augmented reality. It remains, however, a challenging task, particularly for large-scale environments and in presence of significant appearance changes. State-of-the-art methods not only struggle with such scenarios, but are often too resource intensive for certain real-time applications. In this paper we propose HF-Net, a hierarchical localization approach based on a monolithic CNN that simultaneously predicts local features and global descriptors for accurate 6-DoF localization. We exploit the coarse-to-fine localization paradigm: we first perform a global retrieval to obtain location hypotheses and only later match local features within those candidate places. This hierarchical approach incurs significant runtime savings and makes our system suitable for real-time operation. By leveraging learned descriptors, our method achieves remarkable localization robustness across large variations of appearance. Consequently, we demonstrate new state-of-the-art performance on two challenging benchmarks for large-scale 6-DoF localization. The code of our method will be made publicly available.

From Perception to Decision: A Data-driven Approach to End-to-end Motion Planning for Autonomous Ground Robots

Learning from demonstration for motion planning is an ongoing research topic. In this paper we present a model that is able to learn the complex mapping from raw 2D-laser range findings and a target position to the required steering commands for the robot. To our best knowledge, this work presents the first approach that learns a target-oriented end-to-end navigation model for a robotic platform. The supervised model training is based on expert demonstrations generated in simulation with an existing motion planner. We demonstrate that the learned navigation model is directly transferable to previously unseen virtual and, more interestingly, real-world environments. It can safely navigate the robot through obstacle-cluttered environments to reach the provided targets. We present an extensive qualitative and quantitative evaluation of the neural network-based motion planner, and compare it to a grid-based global approach, both in simulation and in real-world experiments.

Empty Cities: Image Inpainting for a Dynamic-Object-Invariant Space

In this paper we present an end-to-end deep learning framework to turn images that show dynamic content, such as vehicles or pedestrians, into realistic static frames. This objective encounters two main challenges: detecting the dynamic objects, and inpainting the static occluded background. The second challenge is approached with a conditional generative adversarial model that, taking as input the original dynamic image and the computed dynamic/static binary mask, is capable of generating the final static image. The former challenge is addressed by the use of a convolutional network that learns a multi-class semantic segmentation of the image. The objective of this network is producing an accurate segmentation and helping the previous generative model to output a realistic static image. These generated images can be used for applications such as virtual reality or vision-based robot localization purposes. To validate our approach, we show both qualitative and quantitative comparisons against other inpainting methods by removing the dynamic objects and hallucinating the static structure behind them. Furthermore, to demonstrate the potential of our results, we conduct pilot experiments showing the benefits of our proposal for visual place recognition. Code has been made available on https://github.com/bertabescos/EmptyCities.

Leveraging Deep Visual Descriptors for Hierarchical Efficient Localization

Many robotics applications require precise pose estimates despite operating in large and changing environments. This can be addressed by visual localization, using a pre-computed 3D model of the surroundings. The pose estimation then amounts to finding correspondences between 2D keypoints in a query image and 3D points in the model using local descriptors. However, computational power is often limited on robotic platforms, making this task challenging in large-scale environments. Binary feature descriptors significantly speed up this 2D-3D matching, and have become popular in the robotics community, but also strongly impair the robustness to perceptual aliasing and changes in viewpoint, illumination and scene structure. In this work, we propose to leverage recent advances in deep learning to perform an efficient hierarchical localization. We first localize at the map level using learned image-wide global descriptors, and subsequently estimate a precise pose from 2D-3D matches computed in the candidate places only. This restricts the local search and thus allows to efficiently exploit powerful non-binary descriptors usually dismissed on resource-constrained devices. Our approach results in state-of-the-art localization performance while running in real-time on a popular mobile platform, enabling new prospects for robotics research.

Reinforced Imitation: Sample Efficient Deep Reinforcement Learning for Map-less Navigation by Leveraging Prior Demonstrations

This work presents a case study of a learning-based approach for target driven map-less navigation. The underlying navigation model is an end-to-end neural network which is trained using a combination of expert demonstrations, imitation learning (IL) and reinforcement learning (RL). While RL and IL suffer from a large sample complexity and the distribution mismatch problem, respectively, we show that leveraging prior expert demonstrations for pre-training can reduce the training time to reach at least the same level of performance compared to plain RL by a factor of 5. We present a thorough evaluation of different combinations of expert demonstrations, different RL algorithms and reward functions, both in simulation and on a real robotic platform. Our results show that the final model outperforms both standalone approaches in the amount of successful navigation tasks. In addition, the RL reward function can be significantly simplified when using pre-training, e.g. by using a sparse reward only. The learned navigation policy is able to generalize to unseen and real-world environments.