Visual-inertial systems rely on precise calibrations of both camera intrinsics and inter-sensor extrinsics, which typically require manually performing complex motions in front of a calibration target. In this work we present a novel approach to obtain favorable trajectories for visual-inertial system calibration, using model-based deep reinforcement learning. Our key contribution is to model the calibration process as a Markov decision process and then use model-based deep reinforcement learning with particle swarm optimization to establish a sequence of calibration trajectories to be performed by a robot arm. Our experiments show that while maintaining similar or shorter path lengths, the trajectories generated by our learned policy result in lower calibration errors compared to random or handcrafted trajectories.
Neural networks (NNs) are widely used for object recognition tasks in autonomous driving. However, NNs can fail on input data not well represented by the training dataset, known as out-of-distribution (OOD) data. A mechanism to detect OOD samples is important in safety-critical applications, such as automotive perception, in order to trigger a safe fallback mode. NNs often rely on softmax normalization for confidence estimation, which can lead to high confidences being assigned to OOD samples, thus hindering the detection of failures. This paper presents a simple but effective method for determining whether inputs are OOD. We propose an OOD detection approach that combines auxiliary training techniques with post hoc statistics. Unlike other approaches, our proposed method does not require OOD data during training, and it does not increase the computational cost during inference. The latter property is especially important in automotive applications with limited computational resources and real-time constraints. Our proposed method outperforms state-of-the-art methods on real world automotive datasets.
Current research on visual place recognition mostly focuses on aggregating local visual features of an image into a single vector representation. Therefore, high-level information such as the geometric arrangement of the features is typically lost. In this paper, we introduce a novel learning-based approach to place recognition, using RGB-D cameras and line clusters as visual and geometric features. We state the place recognition problem as a problem of recognizing clusters of lines instead of individual patches, thus maintaining structural information. In our work, line clusters are defined as lines that make up individual objects, hence our place recognition approach can be understood as object recognition. 3D line segments are detected in RGB-D images using state-of-the-art techniques. We present a neural network architecture based on the attention mechanism for frame-wise line clustering. A similar neural network is used for the description of these clusters with a compact embedding of 128 floating point numbers, trained with triplet loss on training data obtained from the InteriorNet dataset. We show experiments on a large number of indoor scenes and compare our method with the bag-of-words image-retrieval approach using SIFT and SuperPoint features and the global descriptor NetVLAD. Trained only on synthetic data, our approach generalizes well to real-world data captured with Kinect sensors, while also providing information about the geometric arrangement of instances.
Localization of a robotic system within a previously mapped environment is important for reducing estimation drift and for reusing previously built maps. Existing techniques for geometry-based localization have focused on the description of local surface geometry, usually using pointclouds as the underlying representation. We propose a system for geometry-based localization that extracts features directly from an implicit surface representation: the Signed Distance Function (SDF). The SDF varies continuously through space, which allows the proposed system to extract and utilize features describing both surfaces and free-space. Through evaluations on public datasets, we demonstrate the flexibility of this approach, and show an increase in localization performance over state-of-the-art handcrafted surfaces-only descriptors. We achieve an average improvement of ~12% on an RGB-D dataset and ~18% on a LiDAR-based dataset. Finally, we demonstrate our system for localizing a LiDAR-equipped MAV within a previously built map of a search and rescue training ground.
Today's methods of programming mobile manipulation systems' behavior for operating in unstructured environments do not generalize well to unseen tasks or changes in the environment not anticipated at design time. Although symbolic planning makes this task more accessible to non-expert users by allowing a user to specify a desired goal, it reaches its limits when a task or the current environment is not soundly represented by the abstract domain or problem description. We propose a method that allows an agent to autonomously extend its skill set and thus the abstract description upon encountering such a situation. For this, we combine a set of four basic skills (grasp, place, navigate, move) with an off-the-shelf symbolic planner upon which we base a skill sequence exploration scheme. To make the search over skill sequences more efficient and effective, we introduce strategies for generalizing from previous experience, completing sequences of key skills and discovering preconditions. The resulting system is evaluated in simulation using object rearrangement tasks. We can show qualitatively that the skill set extension works as expected and quantitatively that our strategies for more efficient search make the approach computationally tractable.
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 GLoca}, will be made available open source.
Localization of a robotic system within a previously mapped environment is important for reducing estimation drift and for reusing previously built maps. Existing techniques for geometry-based localization have focused on the description of local surface geometry, usually using pointclouds as the underlying representation. We propose a system for geometry-based localization that extracts features directly from an implicit surface representation: the Signed Distance Function (SDF). The SDF varies continuously through space, which allows the proposed system to extract and utilize features describing both surfaces and free-space. Through evaluations on public datasets, we demonstrate the flexibility of this approach, and show an increase in localization performance over state-of-the-art handcrafted surfaces-only descriptors. We achieve an average improvement of ~12% on an RGB-D dataset and ~18% on a LiDAR-based dataset. Finally, we demonstrate our system for localizing a LiDAR-equipped MAV within a previously built map of a search and rescue training ground.
In this paper, we introduce IDOL, an optimization-based framework for IMU-DVS Odometry using Lines. Event cameras, also called Dynamic Vision Sensors (DVSs), generate highly asynchronous streams of events triggered upon illumination changes for each individual pixel. This novel paradigm presents advantages in low illumination conditions and high-speed motions. Nonetheless, this unconventional sensing modality brings new challenges to perform scene reconstruction or motion estimation. The proposed method offers to leverage a continuous-time representation of the inertial readings to associate each event with timely accurate inertial data. The method's front-end extracts event clusters that belong to line segments in the environment whereas the back-end estimates the system's trajectory alongside the lines' 3D position by minimizing point-to-line distances between individual events and the lines' projection in the image space. A novel attraction/repulsion mechanism is presented to accurately estimate the lines' extremities, avoiding their explicit detection in the event data. The proposed method is benchmarked against a state-of-the-art frame-based visual-inertial odometry framework using public datasets. The results show that IDOL performs at the same order of magnitude on most datasets and even shows better orientation estimates. These findings can have a great impact on new algorithms for DVS.
This paper presents a framework for the localization of Unmanned Aerial Vehicles (UAVs) in unstructured environments with the help of deep learning. A real-time rendering engine is introduced that generates optical and depth images given a six Degrees-of-Freedom (DoF) camera pose, camera model, geo-referenced orthoimage, and elevation map. The rendering engine is embedded into a learning-based six-DoF Inverse Compositional Lucas-Kanade (ICLK) algorithm that is able to robustly align the rendered and real-world image taken by the UAV. To learn the alignment under environmental changes, the architecture is trained using maps spanning multiple years at high resolution. The evaluation shows that the deep 6DoF-ICLK algorithm outperforms its non-trainable counterparts by a large margin. To further support the research in this field, the real-time rendering engine and accompanying datasets are released along with this publication.
In this paper, we present our deep learning-based human detection system that uses optical (RGB) and long-wave infrared (LWIR) cameras to detect, track, localize, and re-identify humans from UAVs flying at high altitude. In each spectrum, a customized RetinaNet network with ResNet backbone provides human detections which are subsequently fused to minimize the overall false detection rate. We show that by optimizing the bounding box anchors and augmenting the image resolution the number of missed detections from high altitudes can be decreased by over 20 percent. Our proposed network is compared to different RetinaNet and YOLO variants, and to a classical optical-infrared human detection framework that uses hand-crafted features. Furthermore, along with the publication of this paper, we release a collection of annotated optical-infrared datasets recorded with different UAVs during search-and-rescue field tests and the source code of the implemented annotation tool.