Inertial measurement units (IMUs) suffer from bias and measurement noise, which makes it much more complicated to tackle the problem of inertial odometry (IO). Due to the error propagation over time, while estimating robot position, an inaccurate estimation or a small error will cause the odometry and a localization system unreliable and unusable in a split of seconds. This paper presents a novel triple-channel deep IO network architecture based on the physical and mathematical models of IMUs. The proposed method simulates the noise model in the training phase and becomes robust to noise during testing. Besides, the proposed network architecture also considers the time interval between two consecutive IMU readings (sampling time) so that it is robust to the change of IMU frequency and the missing of IMU information. To the best of our knowledge, this paper is the first work reviewing and analyzing the existing IO methods used by the deep-learning-based visual-IO approaches. The proposed network architecture outperforms all the existing solutions on the IMU readings of the challenging Micro Aerial Vehicle dataset and improves the accuracy by approximately 25%.

Estimating the robot's heading is a crucial requirement in odometry systems which are attempting to estimate the movement trajectory of a robot. Small errors in the orientation estimation result in a significant difference between the estimated and real trajectory, and failure of the odometry system. The odometry problem becomes much more complicated for micro flying robots since they cannot carry massive sensors. In this manner, they should benefit from the small size and low-cost sensors, such as IMU, to solve the odometry problem, and industries always look for such solutions. However, IMU suffers from bias and measurement noise, which makes the problem of position and orientation estimation challenging to be solved by a single IMU. While there are numerous studies on the fusion of IMU with other sensors, this study illustrates the power of the first deep learning framework for estimating the full 3D orientation of the flying robots (as yaw, pitch, and roll in quaternion coordinates) accurately with the presence of a single IMU. A particular IMU should be utilized during the training and testing of the proposed system. Besides, a method based on the Genetic Algorithm is introduced to measure the IMU bias in each execution. The results show that the proposed method improved the flying robots' ability to estimate their orientation displacement by approximately 80% with the presence of a single particular IMU. The proposed approach also outperforms existing solutions that utilize a monocular camera and IMU simultaneously by approximately 30%.

Real-time path planning is crucial for intelligent vehicles to achieve autonomous navigation. In this paper, we propose a novel deep neural network (DNN) based method for real-time online path planning in unknown cluttered environments. Firstly, an end-to-end DNN architecture named online three-dimensional path planning network (OTDPP-Net) is designed to learn 3D local path planning policies. It determines actions in 3D space based on multiple value iteration computations approximated by recurrent 2D convolutional neural networks. Moreover, a path planning framework is also developed to realize near-optimal real-time online path planning. The effectiveness of the proposed planner is further improved by a switching scheme, and the path quality is optimized by line-of-sight checks. Both virtual and real-world experimental results demonstrate the remarkable performance of the proposed DNN-based path planner in terms of efficiency, success rate and path quality. Different from existing methods, the computational time and effectiveness of the developed DNN-based path planner are both independent of environmental conditions, which reveals its superiority in large-scale complex environments. A video of our experiments can be found at: https://youtu.be/gb4nSG4hd6s.

In this article, we propose a deep reinforcement learning (DRL) algorithm as well as a novel tailored neural network architecture for mobile robots to learn navigation policies autonomously. We first introduce a new feature extractor to better acquire critical spatiotemporal features from raw depth images. In addition, we present a double-source scheme so that the experiences are collected from both the proposed model and a conventional planner alternatively based on a switching criterion to provide more diverse and comprehensive samples for learning. Moreover, we also propose a dual-soft-actor–critic architecture to train two sets of networks with different purposes simultaneously. Specifically, the primary network aims to learn the autonomous navigation policy, while the secondary network aims to learn the depth feature extractor. In this way, the learning performance can be improved through decoupling representation learning from policy learning and training the feature extractor separately with more specific goals. Experimental results have demonstrated the remarkable performance of the proposed model. It outperforms both the conventional and the state-of-the-art DRL-based methods consistently in terms of success rate. Meanwhile, it also exhibits higher trajectory quality and better generalization capability compared to existing DRL-based methods. Videos of our experiments are available at https://youtu.be/evjU6bOU3UY or OneDrive.

It is crucial for robots to autonomously steer in complex environments safely without colliding with any obstacles. Compared to conventional methods, deep reinforcement learning-based methods are able to learn from past experiences automatically and enhance the generalization capability to cope with unseen circumstances. Therefore, we propose an end-to-end deep reinforcement learning algorithm in this paper to improve the performance of autonomous steering in complex environments. By embedding a branching noisy dueling architecture, the proposed model is capable of deriving steering commands directly from raw depth images with high efficiency. Specifically, our learning-based approach extracts the feature representation from depth inputs through convolutional neural networks and maps it to both linear and angular velocity commands simultaneously through different streams of the network. Moreover, the training framework is also meticulously designed to improve the learning efficiency and effectiveness. It is worth noting that the developed system is readily transferable from virtual training scenarios to real-world deployment without any fine-tuning by utilizing depth images. The proposed method is evaluated and compared with a series of baseline methods in various virtual environments. Experimental results demonstrate the superiority of the proposed model in terms of average reward, learning efficiency, success rate as well as computational time. Moreover, a variety of real-world experiments are also conducted which reveal the high adaptability of our model to both static and dynamic obstacle-cluttered environments.