It is ubiquitously accepted that during the autonomous navigation of the quadrotors, one of the most widely adopted unmanned aerial vehicles (UAVs), safety always has the highest priority. However, it is observed that the ego airflow disturbance can be a significant adverse factor during flights, causing potential safety issues, especially in narrow and confined indoor environments. Therefore, we propose a novel method to estimate and adapt indoor ego airflow disturbance of quadrotors, meanwhile applying it to trajectory planning. Firstly, the hover experiments for different quadrotors are conducted against the proximity effects. Then with the collected acceleration variance, the disturbances are modeled for the quadrotors according to the proposed formulation. The disturbance model is also verified under hover conditions in different reconstructed complex environments. Furthermore, the approximation of Hamilton-Jacobi reachability analysis is performed according to the estimated disturbances to facilitate the safe trajectory planning, which consists of kinodynamic path search as well as B-spline trajectory optimization. The whole planning framework is validated on multiple quadrotor platforms in different indoor environments.
Distributed pose graph optimization (DPGO) is one of the fundamental techniques of swarm robotics. Currently, the sub-problems of DPGO are built on the native poses. Our validation proves that this approach may introduce an imbalance in the sizes of the sub-problems in real-world scenarios, which affects the speed of DPGO optimization, and potentially increases communication requirements. In addition, the coherence of the estimated poses is not guaranteed when the robots in the swarm fail, or partial robots are disconnected. In this paper, we propose BDPGO, a balanced distributed pose graph optimization framework using the idea of decoupling the robot poses and DPGO. BDPGO re-distributes the poses in the pose graph to the robot swarm in a balanced way by introducing a two-stage graph partitioning method to build balanced subproblems. Our validation demonstrates that BDPGO significantly improves the optimization speed without changing the specific algorithm of DPGO in realistic datasets. What's more, we also validate that BDPGO is robust to robot failure, changes in the wireless network. BDPGO has capable of keeps the coherence of the estimated poses in these situations. The framework also has the potential to be applied to other collaborative simultaneous localization and mapping (CSLAM) problems involved in distributedly solving the factor graph.
In this paper, we present an Efficient Planning System for automated vehicles In highLy interactive envirONments (EPSILON). EPSILON is an efficient interaction-aware planning system for automated driving, and is extensively validated in both simulation and real-world dense city traffic. It follows a hierarchical structure with an interactive behavior planning layer and an optimization-based motion planning layer. The behavior planning is formulated from a partially observable Markov decision process (POMDP), but is much more efficient than naively applying a POMDP to the decision-making problem. The key to efficiency is guided branching in both the action space and observation space, which decomposes the original problem into a limited number of closed-loop policy evaluations. Moreover, we introduce a new driver model with a safety mechanism to overcome the risk induced by the potential imperfectness of prior knowledge. For motion planning, we employ a spatio-temporal semantic corridor (SSC) to model the constraints posed by complex driving environments in a unified way. Based on the SSC, a safe and smooth trajectory is optimized, complying with the decision provided by the behavior planner. We validate our planning system in both simulations and real-world dense traffic, and the experimental results show that our EPSILON achieves human-like driving behaviors in highly interactive traffic flow smoothly and safely without being over-conservative compared to the existing planning methods.
Tail-sitter vertical takeoff and landing (VTOL) unmanned aerial vehicles (UAVs) have the capability of hovering and performing efficient level flight with compact mechanical structures. We present a unified controller design for such UAVs, based on recurrent neural networks. An advantage of this design method is that the various flight modes (i.e., hovering, transition and level flight) of a VTOL UAV are controlled in a unified manner, as opposed to treating them separately and in the runtime switching one from another. The proposed controller consists of an outer-loop position controller and an inner-loop attitude controller. The inner-loop controller is composed of a proportional attitude controller and a loop-shaping linear angular rate controller. For the outer-loop controller, we propose a nonlinear solver to compute the desired attitude and thrust, based on the UAV dynamics and an aerodynamic model, in addition to a cascaded PID controller for the position and velocity tracking. We employ a recurrent neural network (RNN) to approximate the behavior of the nonlinear solver, which suffers from high computational complexity. The proposed RNN has negligible approximation errors, and can be implemented in real-time (e.g., 50 Hz). Moreover, the RNN generates much smoother outputs than the nonlinear solver. We provide an analysis of the stability and robustness of the overall closed-loop system. Simulation and experiments are also presented to demonstrate the effectiveness of the proposed method.
The decentralized state estimation is one of the most fundamental components for autonomous aerial swarm systems in GPS-denied areas, which still remains a highly challenging research topic. To address this research niche, the Omni-swarm, a decentralized omnidirectional visual-inertial-UWB state estimation system for the aerial swarm is proposed in this paper. In order to solve the issues of observability, complicated initialization, insufficient accuracy and lack of global consistency, we introduce an omnidirectional perception system as the front-end of the Omni-swarm, consisting of omnidirectional sensors, which includes stereo fisheye cameras and ultra-wideband (UWB) sensors, and algorithms, which includes fisheye visual inertial odometry (VIO), multi-drone map-based localization and visual object detector. A graph-based optimization and forward propagation working as the back-end of the Omni-swarm to fuse the measurements from the front-end. According to the experiment result, the proposed decentralized state estimation method on the swarm system achieves centimeter-level relative state estimation accuracy while ensuring global consistency. Moreover, supported by the Omni-swarm, inter-drone collision avoidance can be accomplished in a whole decentralized scheme without any external device, demonstrating the potential of Omni-swarm to be the foundation of autonomous aerial swarm flights in different scenarios.
Visual-Inertial odometry (VIO) is known to suffer from drifting especially over long-term runs. In this paper, we present GVINS, a non-linear optimization based system that tightly fuses GNSS raw measurements with visual and inertial information for real-time and drift-free state estimation. Our system is aiming to provide accurate global 6-DoF estimation under complex indoor-outdoor environment where GNSS signals may be largely intercepted or even totally unavailable. To connect global measurements with local states, a coarse-to-fine initialization procedure is proposed to efficiently online calibrate the transformation and initialize GNSS states from only a short window of measurements. The GNSS pseudorange and Doppler shift measurements are then modelled and optimized under a factor graph framework along with visual and inertial constraints. For complex and GNSS-unfriendly areas, the degenerate cases are discussed and carefully handled to ensure robustness. The engineering challenges involved in the system are also included to facilitate relevant GNSS fusion researches. Thanks to the tightly-coupled multi-sensor approach and system design, our system fully exploits the merits of three types of sensors and is capable to seamlessly cope with the transition between indoor and outdoor environments, where satellites are lost and recaptured again. We extensively evaluate the proposed system by both simulation and real-world experiments, and the result demonstrates that our system substantially eliminates the drift of VIO and preserves the local accuracy in spite of noisy GNSS measurements. In addition, experiments also show that our system can gain from even a single satellite while conventional GNSS algorithms need four at lease.
Visual-Inertial odometry is known to suffer from drifting especially over long-term runs. In this paper, we present GVINS, a non-linear optimization based system that tightly fuses GNSS raw measurements with visual and inertial information for real-time and drift-free state estimation. The proposed system combines merits from VIO and GNSS system, thus is able to achieve both local smoothness and global consistency. To associate global measurements with local states, a coarse-to-fine initialization procedure is proposed to efficiently online calibrate the transformation and initialize GNSS states from only a short window of measurements. The GNSS pseudorange and Doppler shift measurements are modelled and optimized under a factor graph framework along with visual and inertial constraints. For complex and GNSS-unfriendly area, the degenerate cases are discussed and carefully handled to ensure robustness. The engineering challenges involved in the system are also included to facilitate relevant GNSS fusion researches. Thanks to the tightly-coupled multi-sensor approach and system design, our estimator is able to recover the position and orientation in the global Earth frame, even with less than 4 satellites being tracked. We extensively evaluate the proposed system on simulation and real-world experiments, and the result demonstrates that our system substantially eliminates the drift of VIO and preserves the accuracy in spite of noisy GNSS measurements.
The collaboration of unmanned aerial vehicles (UAVs), also known as aerial swarm, has become a popular research topic for its practicality and flexibility in plenty of scenarios. However, one of the most fundamental components for autonomous aerial swarm systems in GPS-denied areas, the robust decentralized relative state estimation, remains to be an extremely challenging research topic. In order to address this research niche, the Omni-swarm, an aerial swarm system with decentralized Omni-directional visual-inertial-UWB state estimation, which features robustness, accuracy, and global consistency, is proposed in this paper. We introduce a map-based localization method using deep learning tools to perform relative localization and re-localization within the aerial swarm while achieving the fast initialization and maintaining the global consistency of state estimation. Furthermore, to overcome the sensors' visibility issues with the limited field of view (FoV), which severely affect the performance of the state estimation, Omni-directional sensors, including fisheye cameras and ultra-wideband (UWB) sensors, are adopted. The state estimation module, together with the planning and the control modules, is integrated on the aerial system with Omni-directional sensors to attain the Omni-swarm, and extensive experiments are performed to verify the validity and examine the performance of the proposed framework. According to the experiment result, the proposed framework can achieve centimeter-level relative state estimation accuracy while ensuring global consistency.
Identifying independently moving objects is an essential task for dynamic scene understanding. However, traditional cameras used in dynamic scenes may suffer from motion blur or exposure artifacts due to their sampling principle. By contrast, event-based cameras are novel bio-inspired sensors that offer advantages to overcome such limitations. They report pixel-wise intensity changes asynchronously, which enables them to acquire visual information at exactly the same rate as the scene dynamics. We have developed a method to identify independently moving objects acquired with an event-based camera, i.e., to solve the event-based motion segmentation problem. This paper describes how to formulate the problem as a weakly-constrained multi-model fitting one via energy minimization, and how to jointly solve its two subproblems -- event-cluster assignment (labeling) and motion model fitting -- in an iterative manner, by exploiting the spatio-temporal structure of input events in the form of a space-time graph. Experiments on available datasets demonstrate the versatility of the method in scenes with different motion patterns and number of moving objects. The evaluation shows that the method performs on par or better than the state of the art without having to predetermine the number of expected moving objects.