Navigation In Unknown Environments Research Articles

Efficient micro-mobility path planning without using high-definition maps

Efficient path planning is crucial for the safe autonomous operation of micro-mobility vehicles in unknown environments. When planning paths for micro-mobility, factors, such as the changes in the user's intended destination and user comfort, must be considered. Moreover, for driving in unknown areas, the path planner should not rely on predetermined detailed information like High-Definition maps (HD maps). In this paper, we propose an innovative path planning algorithm for automated driving that solely uses basic perception data from RGB camera, IMU and GPS, thereby eliminating the dependency on HD maps. We initially convert perception data into an occupancy grid map. Subsequently, a global path planner, based on a modified A* algorithm, computes an efficient trajectory, particularly adept to navigation in unknown environments and to scenarios where goal position moves. Additionally, we developed a local planner that optimize multi-clothoid curves using designed constraints to predict the best trajectory. Our experiments, conducted in both simulated and real-world environments, validate the effectiveness of our approach for micro-mobility path planning using only perception data.

Optimizing autonomous navigation in unknown environments: A novel trap avoiding vector field histogram algorithm VFH+T

The Vector Field Histogram Plus (VFH+) algorithm is a cornerstone in robotic navigation, renowned for its efficiency and straightforward implementation across a multitude of environments. Despite its widespread utility, the algorithm's inherent limitations in handling complex obstacle entrapments necessitate refinement. This paper presents an advanced iteration, designated as VFH + T, which incorporates sophisticated memory-based trap recognition and avoidance mechanisms. This enhancement facilitates dynamic adjustment of navigation strategies through the integration of geometrical rules that retrospectively inform path planning decisions. Moreover, the VFH + T algorithm intricately melds the robotic platform's kinematic and dynamic constraints, optimizing real-time navigational commands based on both current sensory input and historical environmental interactions. Empirical simulations validate the enhanced algorithm's proficiency in circumventing navigational traps, improving operational safety and efficiency. Comparative analysis with VFH+ and VFH* algorithms show up to 17 % reduction in traveling distance due to the trap-avoidance technique during navigation. This advancement holds significant implications for enhancing autonomous navigation technologies in various practical applications, from self-driving vehicles to robotic aids in logistics and service industries.

Simultaneous localization and mapping (SLAM)-based robot localization and navigation algorithm

This research paper presents a comprehensive study of the simultaneous localization and mapping (SLAM) algorithm for robot localization and navigation in unknown environments. The SLAM algorithm is a widely used approach for building a map of an environment and estimating the robot’s position within it, which is especially useful in dynamic and unstructured environments. The paper discusses various SLAM techniques, including the Kalman filter (KF) and GraphSLAM algorithms, and their use in probabilistic estimation of the robot’s position and orientation. The paper also explores different path-planning techniques that can be used with the map created by the SLAM algorithm to generate collision-free paths for the robot to navigate toward its goal. The paper also discusses recent advances in deep learning-based SLAM algorithms and their applications in indoor navigation with ORB and RGB-D cameras. The research concludes that SLAM-based robot localization and navigation algorithms are a promising approach for robots navigating in unstructured environments and present various opportunities for future research.

A Hardware Realization Framework for Fuzzy Inference System Optimization

Fuzzy inference systems (FISs) are a key focus for decision-making in embedded systems due to their effectiveness in managing uncertainty and non-linearity. This study demonstrates that optimizing FIS hardware enhances performance, efficiency, and capabilities, improving user experience, heightened productivity, and cost savings. We propose an ultra-low power FIS hardware framework to address power constraints in embedded systems. This framework supports optimizations for conventional arithmetic and Most Significant Digit First (MSDF) computing, ensuring compatibility with MSDF-based sensors. Within the MSDF-computing FIS, fuzzification, inference, and defuzzification processes occur on serially incoming data bits. To illustrate the framework’s efficiency, we implemented it using MATLAB, Chisel3, and Vivado, starting from high-level FIS descriptions and progressing to hardware synthesis. A Scala library in Chisel3 was developed to connect these tools seamlessly, facilitating design space exploration at the arithmetic level. We applied the framework by realizing an FIS for autonomous mobile robot navigation in unknown environments. The synthesis results highlight the superiority of our designs over the MATLAB HDL code generator, achieving a 43% higher clock frequency, and 46% and 67% lower resource and power consumption, respectively.

LiDAR-Based Online Control Barrier Function Synthesis for Safe Navigation in Unknown Environments

LiDAR-Based Online Control Barrier Function Synthesis for Safe Navigation in Unknown Environments

Combining Motion Planner and Deep Reinforcement Learning for UAV Navigation in Unknown Environment

Combining Motion Planner and Deep Reinforcement Learning for UAV Navigation in Unknown Environment

Spatial memory-augmented visual navigation based on hierarchical deep reinforcement learning in unknown environments

Visual navigation in unknown environments poses significant challenges due to the presence of many obstacles and low-texture scenes. These factors may cause frequent collisions and tracking failure of feature-based visual Simultaneous Localization and Mapping (vSLAM). To avoid these issues, this paper proposes a spatial memory-augmented visual navigation system that combines a vSLAM module, a conventional global planner module, and a Hierarchical Reinforcement Learning (HRL)-based local planner module. Firstly, a real-time vSLAM named Salient-SLAM is proposed to augment the performance of visual navigation. Salient-SLAM creates a navigation mapping thread by combining a saliency prediction model to build a navigation map that categorizes environmental regions as occupied, explored, or noticeable. Spatial memory that contains spatial abstraction and saliency information of the environment can be further formed by encoding navigation maps, which helps the agent determine an optimal path towards its destination. An open-sourced saliency dataset is proposed to train the saliency prediction model by mimicking the visual attention mechanism. Secondly, a HRL method is proposed to automatically decompose local planning into a high-level policy selector and several low-level policies, where the latter produces actions to interact with the environment. We maximize entropy and minimize option correlation in learning low-level policies, aiming at acquiring diverse and independent behaviors. The simulation results show that the proposed HRL method outperforms competitive baselines by 6.29–10.85 % on Success Rate (SR) and 3.87–11.1 % on Success weighted by Path Length (SPL) metrics. By incorporating the spatial memory, SR, and SPL metrics can be augmented by an average of 9.85 % and 10.89 %, respectively.

Event-Triggered Hierarchical Planner for Autonomous Navigation in Unknown Environment

End-to-end deep neural network (DNN)-based motion planners have shown great potential in high-speed autonomous UAV flight. Yet, most existing methods only employ a single high-capacity DNN, which typically lacks generalization ability and suffers from high sample complexity. We propose a novel event-triggered hierarchical planner (ETHP), which exploits the bi-level optimization nature of the navigation task to achieve both efficient training and improved optimality. Specifically, we learn a depth-image-based end-to-end motion planner in a hierarchical reinforcement learning framework, where the high-level DNN is a reactive collision avoidance rerouter triggered by the clearance distance, and the low-level DNN is a goal-chaser that generates the heading and velocity references in real time. Our training considers the field-of-view constraint and explores the bi-level structural flexibility to promote the spatio–temporal optimality of planning. Moreover, we design simple yet effective rules to collect hindsight experience replay buffers, yielding more high-quality samples and faster convergence. The experiments show that, compared with a single-DNN baseline planner, ETHP significantly improves the success rate and generalizes better to the unseen environment.

Visual aid for unmanned aircraft navigation in unknown environments

This study presents a visual-aided inertial navigation technique that can be used for unmanned aircraft in unknown environments. An angular and linear velocity estimation algorithm, which is based on the solution of the Wahba’s problem, is developed using sequential images for visual odometry. It is possible that the visual sensors do not receive continuous measurements throughout the mission, for example, when a sufficient number of features cannot be detected by the camera. Considering that a closed loop Extended Kalman Filter algorithm is designed for integration of visual odometry measurements with the inertial measurements to have accurate pose estimation throughout the flight.

Cubature H∞ Filter based Simultaneous Localization and Mapping

For many real-real applications, autonomous navigation is necessary for many vehicles, including ground, underwater, and aerial vehicles. Simultaneous Localization and Mapping (SLAM) is an important approach for autonomous navigation in unknown environments and/or GPS-denied areas. In SLAM, by using the sensors embedded in the vehicle, the vehicle simultaneously builds a map and localise in that map. In this paper, a solution to the SLAM is proposed using cubature H∞filter (CH∞F). CH∞F is a derivative-free filter, which can deal with highly nonlinear and Gaussian or non-Gaussian systems. It has the desired features of both the cubature Kalman filter and H∞filter, deals with nonlinear and uncertain sensor dynamics. In this paper, CH∞F has been proposed for the SLAM application. Different simulation scenarios are considered and compared.

Governor-parameterized barrier function for safe output tracking with locally sensed constraints

This paper considers output tracking with time-varying constraints, obtained from online sensor measurements, relevant to autonomous system navigation in unknown environments. Inspired by reference governor techniques, we introduce a virtual governor system, whose state specifies an output regulation point for the actual system and is controlled to adaptively track an output reference without violating the constraints. Our main contribution is a governor-parameterized barrier function (PBF) that quantifies the trade-off between safety (distance from constraint violation) and system energy (output-regulation Lyapunov function). The PBF defines a local safe set that varies as the system-governor state or the sensor measurements change. This safe set induces a governor control law, which guarantees safe and stable output tracking for the real system. We demonstrate our adaptive output-tracking controller on a feedback-linearizable system navigating in an unknown environment, where obstacle distances are measured online.

A self-rotating, single-actuated UAV with extended sensor field of view for autonomous navigation.

Uncrewed aerial vehicles (UAVs) rely heavily on visual sensors to perceive obstacles and explore environments. Current UAVs are limited in both perception capability and task efficiency because of a small sensor field of view (FoV). One solution could be to leverage self-rotation in UAVs to extend the sensor FoV without consuming extra power. This natural mechanism, induced by the counter-torque of the UAV motor, has rarely been exploited by existing autonomous UAVs because of the difficulties in design and control due to highly coupled and nonlinear dynamics and the challenges in navigation brought by the high-rate self-rotation. Here, we present powered-flying ultra-underactuated LiDAR (light detection and ranging) sensing aerial robot (PULSAR), an agile and self-rotating UAV whose three-dimensional position is fully controlled by actuating only one motor to obtain the required thrust and moment. The use of a single actuator effectively reduces the energy loss in powered flights. Consequently, PULSAR consumes 26.7% less power than the benchmarked quadrotor with the same total propeller disk area and avionic payloads while retaining a good level of agility. Augmented by an onboard LiDAR sensor, PULSAR can perform autonomous navigation in unknown environments and detect both static and dynamic obstacles in panoramic views without any external instruments. We report the experiments of PULSAR in environment exploration and multidirectional dynamic obstacle avoidance with the extended FoV via self-rotation, which could lead to increased perception capability, task efficiency, and flight safety.

A Dynamic Scene Vision SLAM Method Incorporating Object Detection and Object Characterization

Simultaneous localization and mapping (SLAM) based on RGB-D cameras has been widely used for robot localization and navigation in unknown environments. Most current SLAM methods are constrained by static environment assumptions and perform poorly in real-world dynamic scenarios. To improve the robustness and performance of SLAM systems in dynamic environments, this paper proposes a new RGB-D SLAM method for indoor dynamic scenes based on object detection. The method presented in this paper improves on the ORB-SLAM3 framework. First, we designed an object detection module based on YOLO v5 and relied on it to improve the tracking module of ORB-SLAM3 and the localization accuracy of ORB-SLAM3 in dynamic environments. The dense point cloud map building module was also included, which excludes dynamic objects from the environment map to create a static environment point cloud map with high readability and reusability. Full comparison experiments with the original ORB-SLAM3 and two representative semantic SLAM methods on the TUM RGB-D dataset show that: the method in this paper can run at 30+fps, the localization accuracy improved to varying degrees compared to ORB-SLAM3 in all four image sequences, and the absolute trajectory accuracy can be improved by up to 91.10%. The localization accuracy of the method in this paper is comparable to that of DS-SLAM, DynaSLAM and the two recent target detection-based SLAM algorithms, but it runs faster. The RGB-D SLAM method proposed in this paper, which combines the most advanced object detection method and visual SLAM framework, outperforms other methods in terms of localization accuracy and map construction in a dynamic indoor environment and has a certain reference value for navigation, localization, and 3D reconstruction.

Onboard Observation Planning for Sequential Image-based Planetary Landing Navigation in Unknown Environments

Autonomous navigation based on sequential images is widely accepted as an effective method to guarantee pinpoint landing and precise obstacle avoidance in planetary landings. Observing a large number of landmarks and processing a large number of images places a computational burden on landers with limited computational resources, but existing studies lack observation planning methods for landmarks in unknown environments that can be operated autonomously on landers. In this paper, we analyze the observability of a vision-aided inertial navigation (VAIN) system and propose an observation planning strategy. The minimum number of landmarks and the minimum number of observations are obtained from the observability analysis, which is the boundary condition for observation planning. The landmark configuration planning in the observation planning strategy optimizes only univariate convex functions to efficiently select a small number of landmarks in unknown environments with high navigation accuracy, and the observation interval planning adaptively reduces the number of observations without significantly affecting the navigation accuracy. Simulation results verify the correctness of the observability analysis results, and it is found that the proposed observation planning strategy outperforms traditional observability degrees in terms of both improved navigation accuracy and computational speed when observing a small number of landmarks, and can effectively reduce the number of observations.

Autonomous Navigation in Unknown Environments With Sparse Bayesian Kernel-Based Occupancy Mapping

This article focuses on online occupancy mapping and real-time collision checking onboard an autonomous robot navigating in a large unknown environment. Commonly used voxel and octree map representations can be easily maintained in a small environment but have increasing memory requirements as the environment grows. We propose a fundamentally different approach for occupancy mapping, in which the boundary between occupied and free space is viewed as the decision boundary of a machine learning classifier. This work generalizes a kernel perceptron model which maintains a very sparse set of support vectors to represent the environment boundaries efficiently. We develop a probabilistic formulation based on relevance vector machines, handling measurement noise, and probabilistic occupancy classification, supporting autonomous navigation. We provide an online training algorithm, updating the sparse Bayesian map incrementally from streaming range data, and an efficient collision-checking method for general curves, representing potential robot trajectories. The effectiveness of our mapping and collision checking algorithms is evaluated in tasks requiring autonomous robot navigation and active mapping in unknown environments.

Online Mapping and Motion Planning Under Uncertainty for Safe Navigation in Unknown Environments

Safe autonomous navigation is an essential and challenging problem for robots operating in highly unstructured or completely unknown environments. Under these conditions, not only robotic systems must deal with limited localization information but also their maneuverability is constrained by their dynamics and often suffers from uncertainty. In order to cope with these constraints, this article proposes an uncertainty-based framework for mapping and planning feasible motions online with probabilistic safety guarantees. The proposed approach deals with the motion, probabilistic safety, and online computation constraints by: 1) incrementally mapping the surroundings to build an uncertainty-aware representation of the environment and 2) iteratively (re)planning trajectories to goal that is kinodynamically feasible and probabilistically safe through a multilayered sampling-based planner in the belief space. In-depth empirical analyses illustrate some important properties of this approach, namely: 1) the multilayered planning strategy enables rapid exploration of the high-dimensional belief space while preserving asymptotic optimality and completeness guarantees and 2) the proposed routine for probabilistic collision checking results in tighter probability bounds in comparison to other uncertainty-aware planners in the literature. Furthermore, real-world in-water experimental evaluation on a nonholonomic torpedo-shaped autonomous underwater vehicle and simulated trials in an urban environment on an unmanned aerial vehicle demonstrate the efficacy of the method and its suitability for systems with limited onboard computational power. Note to Practitioners—Emergent robotic applications require operating in previously unmapped scenarios. This article presents a unified mapping–planning strategy that enables robots to navigate autonomously and safely in harsh environments.

Multi-Robot Navigation in Unknown Environment Based on Deep Reinforcement Learning

Günümüzde mobil robotların navigasyon problemini derin takviyeli öğrenme (DRL) ile çözmeye çalışmak ilgi çekici konulardan birisi haline gelmiştir. Tekli mobil robotlarda DRL yüksek başarı oranlarına ulaşmıştır. Çoklu robot sistemlerinde ise, problemin karmaşıklığı üstel bir şekilde arttığı için maliyeti yüksek ve daha zorlu iş haline gelmektedir. Bu çalışmada ise DRL ile çoklu robot navigasyonu problemine çözüm getirilmeye çalışılmıştır. Önerilen yaklaşımdaki sistemde eşzamanlı bir ortam, bu ortamda birden fazla robot, hedef, engel bulunmaktadır. Ortamda robotlar sırasıyla eylem seçerek, hareket ederler. Aynı zamanda robotlar kendilerinden başka robotlar için dinamik bir engel işlevi görmektedir. Robotlar kendi hedeflerine en kısa yoldan herhangi bir çarpışma yaşamadan ulaşmaya çalışırlar. Aynı zamanda robotlar bir başka robotla çarpışmayacak şekilde veya bir başka robotun rotasını uzatmayacak şekilde yol planlaması yapmaya çalışırlar. Bunları sağlayabilmek için çok ajanlı deep q-network (DQN) algoritması, hedefe yönelik bir durum verisi, güçlendirilmiş adaptif ödül mekanizması kullanılmıştır. Önerilen yaklaşım doğrultusunda oluşturulan sistem tek bir robotun navigasyon başarısı, çoklu robot sisteminin navigasyon başarısı, birim-kare başına düşen robot sayısına göre başarı oranı olarak değerlendirilmiştir. Bu değerlendirmeler önerilen yaklaşımın performansını doğrulamıştır.

High-Order Control Barrier Functions

We approach the problem of stabilizing a dynamical system while optimizing a cost and satisfying safety constraints and control limitations. For (nonlinear) affine control systems and quadratic costs, it has been shown that control barrier functions (CBFs) guaranteeing safety and control Lyapunov functions (CLFs) enforcing convergence can be used to (conservatively) reduce the optimal control problem to a sequence of quadratic programs (QPs). Existing works in this category have two main limitations. First, with one exception, they are based on the assumption that the relative degree of the system with respect to a function enforcing a safety constraint is one. Second, the QPs can easily become infeasible, in particular for problems with many safety constraints and tight control limitations. We propose high-order CBFs (HOCBFs), which can accommodate systems of arbitrary relative degrees. For each safety constraint, by using Lyapunov-like conditions, we construct a set of controls that renders the intersection of a set of sets forward invariant, which implies the satisfaction of the original constraint. We formulate optimal control problems with constraints given by HOCBF and CLF, and propose two methods—the penalty method and the parameterization method—to address the feasibility problem. Finally, we show how our methodology can be extended for safe navigation in unknown environments with long-term feasibility. We illustrate the proposed framework on adaptive cruise control and robot control problems.

FASTER: Fast and Safe Trajectory Planner for Navigation in Unknown Environments

Planning high-speed trajectories for UAVs in unknown environments requires algorithmic techniques that enable fast reaction times to guarantee safety as more information about the environment becomes available. The standard approaches that ensure safety by enforcing a “stop” condition in the free-known space can severely limit the speed of the vehicle, especially in situations where much of the world is unknown. Moreover, the ad-hoc time and interval allocation scheme usually imposed on the trajectory also leads to conservative and slower trajectories. This work proposes FASTER (Fast and Safe Trajectory Planner) to ensure safety without sacrificing speed. FASTER obtains high-speed trajectories by enabling the local planner to optimize in both the free-known and unknown spaces. Safety is ensured by always having a safe back-up trajectory in the free-known space. The MIQP formulation proposed also allows the solver to choose the trajectory interval allocation. FASTER is tested extensively in simulation and in real hardware, showing flights in unknown cluttered environments with velocities up to 7.8 m/s, and experiments at the maximum speed of a skid-steer ground robot (2 m/s).

A Novel Neural Multi-Store Memory Network for Autonomous Visual Navigation in Unknown Environment

Learning to achieve a user-specified objective from a random position in unseen environments is challenging for image-guided navigation agents. The abilities of long-horizon reasoning and semantic understanding are still lacking. Inspired by the human memory mechanism, we introduce a neural multi-store memory network to the reinforcement learning framework for target-driven visual navigation. The proposed memory network utilizes three temporal stages of memory to build time dependency for better scene understanding. Sensory memory encodes observations and embeds transient information into working memory, which is short-term and realized by a gated recurrent neural network (RNN). Then, the long-term memory stores the latent state from each step of the RNN into a single slot. Finally, a self-attention reading mechanism is designed to retrieve goal-related information from long-term memory. In addition, to improve the scene generalization capability of the agent, we facilitate training of the visual representation with a self-supervised auxiliary task and image augmentation. This method can navigate agents in unknown visual-realistic environments using only egocentric observations, without the need for any position sensors or pretrained models. The evaluation results on the Matterport3D dataset through the Habitat simulator demonstrate that our method outperforms the state-of-the-art approaches.