Unmanned Systems

Self-navigation, referred as the capability of automatically reaching the goal while avoiding collisions with obstacles, is a fundamental skill required for mobile robots. Recently, deep reinforcement learning (DRL) has shown great potential in the development of robot navigation algorithms. However, it is still difficult to train the robot to learn goal-reaching and obstacle-avoidance skills simultaneously. On the other hand, although many DRL-based obstacle-avoidance algorithms are proposed, few of them are reused for more complex navigation tasks. In this paper, a novel danger-aware adaptive composition (DAAC) framework is proposed to combine two individually DRL-trained agents, obstacle-avoidance and goal-reaching, to construct a navigation agent without any redesigning and retraining. The key to this adaptive composition approach is that the value function outputted by the obstacle-avoidance agent serves as an indicator for evaluating the risk level of the current situation, which in turn determines the contribution of these two agents for the next move. Simulation and real-world testing results show that the composed Navigation network can control the robot to accomplish difficult navigation tasks, e.g. reaching a series of successive goals in an unknown and complex environment safely and quickly.

In recent years, Unmanned Aerial Systems (UASs) development and application have achieved remarkable growth. With the advancement of technology, UASs nowadays feature more advanced autonomous capabilities than ever before. In order to achieve autonomous behavior, intelligent systems are required to be incorporated to support system learning, control and decision-making. With these capabilities, UASs can learn from their past experiences, through interacting with the task environment to adapt their behavior to enhance their future performance. Machine learning is one of the most commonly used techniques for UASs to acquire knowledge from their experience, and research in this area is still developing. In this study, Reinforcement Learning (RL) algorithms were used on autonomous aerial systems to achieve adaptive behavior and decision-making capabilities. The effects of UAS sensor sensitivity, as modeled through Signal Detection Theory (SDT), on the ability of RL algorithms to accomplish a target localization task were investigated. Three levels of sensor sensitivity were simulated and compared to the results of the same system using a perfect sensor, with the consideration of two RL algorithms, namely, Temporal Difference (TD) and Monte Carlo (MC) methods. Target localization and identification task were used as the test bed, and a hierarchical architecture was developed with two distinct agents. Mission performance was analyzed using multiple metrics, including episodic reward and the time taken to locate all targets. Statistical analyses were carried out to detect significant differences in the comparison of steady-state behavior of different factors. Results were discussed, and future research direction was given at the end of the paper.

In this paper, we study the practical fixed-time event-triggered time-varying formation tracking problem of leader-follower multi-agent systems with multi-dimensional dynamics. Fixed-time event-triggered control schemes with continuous communication and intermittent communication are developed, respectively. Continuous communication and measurement are avoided, and computation cost is reduced greatly in the latter scheme. And the settling time is to be specified regardless of initial states of agents. Meanwhile, tracking errors are adjustable as desired with expected settling time. It is demonstrated that time-varying formation tracking can be achieved under the two proposed control schemes and Zeno behavior can be excluded. Finally, numerical examples are provided to illustrate the effectiveness of the proposed control strategies.

Geometry and mass of an aircraft are important factors in flight mechanics and in the calculations of stability and natural frequencies of its flight modes, which are of great importance in controller design process. In this paper, comparison between the formulae of the large aircraft applied on small UAVs scale, XFLR5 as a numerical program and experimental data obtained from flight tests is made to investigate their accuracy. A method to validate natural frequencies for UAVs is presented. It is found that for the phugoid mode, methods of Roskam (exact), Ostoslavsky, and XFLR5 estimate the frequency within range of the experimental results while the methods of Roskam (approximation) and Hull overestimate it and should not be applied in case of small UAVs. Considering the short-period mode, all methods can predict the actual frequency with acceptable accuracy.

The interest in building hybrid Unmanned Aerial Vehicles (UAVs) is increasing intensively due to its capability to perform Vertical Take-Off and Landing (VTOL), in addition to forward flight. With this capability, the hybrid UAVs are highly on demand in various industries. In this paper, a fixed-wing VTOL UAV with a novel configuration of a dual rotor-embedded wing was designed and developed. The methodology used in the design process adopted the traditional sizing and aerodynamic estimation method with advanced computational simulations and estimation approaches. The design was determined based on a thorough analysis of weight contribution, aerodynamics, propulsion, and stability and control. The results show that the UAV’s preliminary design has successfully reached a total weight of 1.318 kg, achieved a high lift-to-drag ratio of approximately 4, and ensured stable flights with Level 1 flying qualities. A fixed-wing VTOL prototype was developed and fabricated based on the final design parameters using a low-cost hand lay-up process.

This paper is focused on analyzing effects of several significant parameters on the performance of an immunity-inspired methodology for autonomous navigation of unmanned air vehicles when measurements from global navigation satellite systems (GNSS) or similar current sources, including external information of opportunity, are not available. An artificial immune system (AIS) provides corrections to a dead reckoning algorithm for adequate estimates of vehicle position and velocity. Parameter effects are assessed and analyzed through simulation in terms of trajectory tracking errors during autonomous flight.

Swing oscillation is widely observed among indoor miniature autonomous blimps (MABs) due to their underactuated design and unique aerodynamic shape. This paper presents the modeling, identification and control system design that reduce the swing oscillation of an MAB during hovering flight. We establish a dynamic model to describe the swing motion of the MAB. The model parameters are identified from both physical measurements, computer modeling and experimental data captured during flight. A control system is designed to stabilize the swing motion with features including low latency and center-of-mass (CM) position estimation. The modeling and control methods are verified with the Georgia-Tech Miniature Autonomous Blimp (GT-MAB) during hovering flight. The experimental results show that the proposed methods can effectively reduce the swing oscillation of GT-MAB.