Integration of Symbolic Task Planning into Operations within an Unstructured Environment

With the expansion of human activities into mountainous regions, jungles, deserts, rural roads, and off-road terrains, there is an increasing demand for reliable navigation and location services in wild unstructured environments. Unlike urban environments, where established methodologies exist for constructing navigation maps, roadless unstructured environments lack comprehensive frameworks for navigation map construction. The conventional waypoint-based structures, which are well-suited to urban environments, are often ill-suited to the expansive and unstructured nature of field regions. Moreover, the absence of predefined user paths necessitates a fundamentally different approach to map construction. To address this challenge, we propose a novel method for generating navigation maps in unstructured roadless environment. New methodology leverages remote sensing as input for environmental perception, translating user traversability into geographical parameters and constructing a navigation mesh as a computational map. Compared with existing methods, the new method can adapt to large-scale unstructured environments. To validate the proposed method, reliability sampling tests and operational experiments were conducted on traversable area delineation and the navigation map generation. The experimental results indicate an 84% accuracy in traversable area analysis, with the constructed navigation map effectively supporting positioning and path planning while significantly reducing computational complexity in large-scale path planning tasks. The navigation mesh generated through this method effectively enhances the implementation of navigation and positioning services in off-road and roadless environments. The proposed method facilitates the construction of navigation maps capable of delivering navigation and localization services without requiring human presence in the target area.

Advanced robots are desired to improve their reasoning ability in increasingly practical situations to quickly respond to urgent challenges such as search and rescue, public security, and autonomous driving. Advances in sensor technology and intelligent algorithms are accelerating the development of autonomous systems, allowing them to interact with dynamic environments more independently and intelligently, completing relatively complicated tasks. Nevertheless, the safety and security problems are yet to be comprehensively addressed. Currently, many efforts have been made to solve this problem by improving the unimodal perception ability of intelligent systems. Methods using surveillance cameras to collect large amounts of visual data and process them using deep networks. Various types of range scanner can sense and reconstruct the surrounding environment through precise distance measurements. However, in the above cases, there may be a lack of training data, fixed cameras cannot adequately and dynamically model the surroundings, unimodal analysis is hard to capture both appearance and depth information. Therefore, higher levels of perception and reasoning abilities are required to handle unexpected conditions and scenarios efficiently. In such cases, mobile robots should be fully aware of the dynamic environment, prioritize, and continuously analyze critical situations, share information, and collaboration under limited computing power and resources. Furthermore, considering the robots are operating alongside humans, reliable and interpretable robot behavior is highly preferred for more natural interactions.
\n
\nThis study aims to develop reasoning strategies for autonomous robots to improve robotic intelligence under different assumptions and conditions. The framework allows one or several robots to address safety or security problems in a targeted manner in partially known environments, where time, dynamics, and interactions play a significant role. The objective is to identify the unique individual whose activity, in space and time, appear different from the other people in the scene. The activities considered not only the motion pattern, but also the object associated with this person. Unlike traditional abnormal detection, the uniqueness reasoning in this work does not require a predefined expected pattern. A modular analysis is also applied to decompose the entire reasoning process into submodules such as perception, analysis, and inference, to achieve algorithmic flexibility and interpretability. Probabilistic modeling is used to associate spatial relationships between semantic labels and their temporal changes. The relationships are described in either instant spatial spaces (semantic-interaction feature) or spatiotemporal spaces (spatiotemporal feature), and it provides essential information for robot navigation, situation awareness, and task planning. Unlike existing research, this is the first time that such a mission is implemented on mobile robot platforms by using the probabilistic fusion of multimodal information.
\n
\nConsidering how evidence information is obtained and linked in the process of reasoning, we study the problem of uniqueness reasoning at three levels. The first level is called knowledge-based single robot uniqueness reasoning and runs on a single robot platform. At this level, we focus on a knowledge-based approach, where knowledge is provided in terms of how motion and an object associated with a person can be used to infer his/her uniqueness, as determined by human expertise. Because such a method has advantages in dealing with structured missions and with limited training data. Qualitative rules are applied to extract human activities from observations, and then the uniqueness of each person is judged by associating the prior knowledge with the performed activities. Experiments were conducted in indoor environments with various degrees of occlusion, and the experimental results showed the rationality and accuracy of the reasoning.
\n
\nHowever, though the knowledge-based method can successfully address specific tasks, it lacks flexibility and generality to adapt to different situations. The assumption of prior knowledge should be replaced by general analytical modeling. Thus, the second level is analytics-based single robot uniqueness reasoning. For one thing, it applies quantitative analysis to model human activities from observations rather than using qualitative rules. For another, instead of leveraging prior knowledge, the distribution of the features characterizing a human activity is constructed and the activity of an individual is analyzed within the distribution to determine if it is unique. Experiments were conducted in both indoor and urban outdoor environments. The experimental results demonstrated the rationality, accuracy, and efficiency of the reasoning.
\n
\nMoreover, since many applications require to work in an unstructured and large-scale environment as well as a long-term operation, the sensing and reasoning capabilities of a single robot are limited by occlusion, sensor failure, and narrow field of view. Robots are desired to share information and perform collaborative reasoning. Therefore, if say the first two levels are mainly using sensory data to implement the algorithm, the third level is more focused on applying the algorithm to the robot platform. The third level is analytics-based multi-robot uniqueness reasoning, in which a multi-robot system is adopted as the platform. By obtaining the relative pose between robots, local observations can be transformed and transmitted among the multi-robot system. Since it is a distributed system, each robot still first performs its local uniqueness reasoning in the case of long-distance and poor communication. Meanwhile, the system performs a re-judgment based on the shared global observation and then shares the judgment results back to each robot. Experiments were carried out in various unstructured environments and contained day and night situations. The experimental results showed the rationality, accuracy, and robustness of the reasoning. This is the first time that reasoning is categorized by considering the way of obtaining and linking evidence information. This study has potential applications in a variety of situations, and it can serve as a guide for further robotic motion planning and human-robot interaction.

Purpose – Reviews the benefits and potential application of tactile sensors for use with robots.Design/methodology/approach – Includes the most recent advances in both the design/manufacturing of various tactile sensors and their applications in different industries. Although these types of sensors have been adopted in a considerable number of areas, the applications such as, medical, agricultural/livestock and food, grippers/manipulators design, prosthetic, and environmental studies have gained more popularity and are presented in this paper.Findings – Robots can perform very useful and repetitive tasks in controlled environments. However, when the robots are required to handle the unstructured and changing environments, there is a need for more elaborate means to improve their performance. In this scenario, tactile sensors can play a major role. In the unstructured environments, the robots must be able to grasp objects (or tissues, in the case of medical robots) and move objects from one location to ano...

There are many sources of uncertainty facing the fuzzy logic controller (FLC) for autonomous mobile robots navigating in changing and dynamic unstructured environments. The traditional type-1 FLC using precise type-1 fuzzy sets cannot fully handle such uncertainties. A type-2 fuzzy logic controller (FLC) using type-2 fuzzy sets can handle such uncertainties to produce a better performance. In this paper, we present the type-2 FLC and its novel application for the real time control of mobile robots. We used the type-2 FLC to implement different robotic behaviours on different robotic platforms in indoor and outdoor unstructured and challenging environments. The type-2 FLCs dealt with the uncertainties facing mobile robots in unstructured environments and resulted in a very good performance that outperformed the type-1 FLCs whilst using smaller rule bases.

In recent years, the perceptual capabilities of robots have been significantly enhanced. However, the task execution of the robots still lacks adaptive capabilities in unstructured and dynamic environments. In this paper, we propose an ontology based autonomous robot task processing framework (ARTProF), to improve the robot's adaptability within unstructured and dynamic environments. ARTProF unifies ontological knowledge representation, reasoning, and autonomous task planning and execution into a single framework. The interface between the knowledge base and neural network-based object detection is first introduced in ARTProF to improve the robot's perception capabilities. A knowledge-driven manipulation operator based on Robot Operating System (ROS) is then designed to facilitate the interaction between the knowledge base and the robot's primitive actions. Additionally, an operation similarity model is proposed to endow the robot with the ability to generalize to novel objects. Finally, a dynamic task planning algorithm, leveraging ontological knowledge, equips the robot with adaptability to execute tasks in unstructured and dynamic environments. Experimental results on real-world scenarios and simulations demonstrate the effectiveness and efficiency of the proposed ARTProF framework. In future work, we will focus on refining the ARTProF framework by integrating neurosymbolic inference.

Visual perception has become core technology in autonomous robotics to identify and localize objects of interest to ensure successful and safe task execution. As part of the recently concluded Robotics Collaborative Technology Alliance (RCTA) program, a collaborative research effort among government, academic, and industry partners, a vision acquisition and processing pipeline was developed and demonstrated to support manned-unmanned team ing for Army relevant applications. The perception pipeline provided accurate and cohesive situational awareness to support autonomous robot capabilities for maneuver in dynamic and unstructured environments, collaborative human-robot mission planning and execution, and mobile manipulation. Development of the pipeline involved a) collecting domain specific data, b) curating ground truth annotations, e.g., bounding boxes, keypoints, c) retraining deep networks to obtain updated object detection and pose estimation models, and d) deploying and testing the trained models on ground robots. We discuss the process of delivering this perception pipeline under limited time and resource constraints due to lack of a priori knowledge of the operational environment. We focus on experiments conducted to optimize the models despite using data that was noisy and exhibited sparse examples for some object classes. Additionally, we discuss our augmentation techniques used to enhance the data set given skewed class distributions. These efforts highlight some initial work that directly relates to learning and updating visual perception systems quickly in the field under sudden environment or mission changes.

The student demonstrations in Beijing after the death of Hu Yaobang, former General Secretary of the Communist Party of China, on 15 April 1989 and the subsequent developments leading to the brutal military crackdown on Beijing students on 3-4 June this year have highlighted in the strongest possible way the importance of democracy and freedom in China and Hong Kong. Since 1984 Hong Kong people have become increasingly aware that their future depends on developments in China. But it is only over the past three months that they have established strong links with their compatriots in China, while intensely following the tragic events there. There has emerged the conviction that if freedom, human rights and democracy cannot be guaranteed in China they cannot be well protected in Hong Kong after 1997. When over one million Hong Kong people marched for democracy and freedom in China on 21 May 1989, 90 per cent were marching for the first time in their lives. They were motivated by anger and shock at what was happening in China, as well as despair and insecurity about the territory's future. A vast majority of them marched again on the two following Sundays. During the negotiations of 1982-4 over the future of Hong Kong between Britain and China, the Chinese leadership promised the Hong Kong community 'gangren zhigang'-self-administration. The Hong Kong government, in its turn, pledged in its Green Paper of July 1984 on the future development of representative government in Hong Kong 'to develop progressively a system of government the authority for which is firmly rooted in Hong Kong, which is able to represent authoritatively the views of the people of Hong Kong and which is more directly accountable to the people of Hong Kong.'1 The positions of the Chinese and British governments were a boost to the morale of the advocates of democracy in Hong Kong. Even ordinary citizens without much interest in politics saw the establishment of a Hong Kong Special Administrative Region (SAR) with a high degree of autonomy and democracy, as stipulated in the Joint Declaration that resulted from the negotiations in December 1984, as a natural development for the territory,2 given that the British colonial role was to terminate in 1997 and that none of the parties concerned wanted the future SAR to be administered directly by Beijing. A government with a high degree of autonomy and democracy would, it was hoped, be an important guarantee of the 50-year period of maintenance of the status quo in Hong Kong stipulated in the Declaration.

With China's resumption of sovereignty over Macau on 20th December 1999, another step was taken towards the reunification of Greater China. The reunification of Macau as of Hong Kong is based on the principle of “one country, two systems’, under which the socialist systems of the People's Republic of China are not applied in these territories. Instead most constituents of their previous economic, legal and social systems are preserved. In either case China negotiated what are called Joint Declarations for the resumption of sovereignty with the colonial power, under which the terms of “one country, two systems’ were spelled out. China undertook to give effect to the Declarations in Basic Laws, passed by its National People's Congress. Except for defence and foreign affairs, most matters are vested in the new entities, called Special Administrative Regions. The Basic Laws describe the constitutional system established for the regions as being characterised by a “high degree of autonomy’. As such they are an interesting addition to autonomy systems which are increasingly being applied as solutions to problems of divided societies. But the institutional support for the autonomy is particularly weak, and a closer examination of the articulation of the regions with the central authorities suggests that the primary concern in establishing the special administrative regions is less the automony for the people of Hong Kong or Macau as finding a framework for managing different economic systems from those on the mainland (I have developed these arguments in Ghai 1999).

Kate Rutter is a senior practitioner at Adaptive Path. She blogs at www.adaptivepath.com or at her personal site www.intelleto.com. Her email address is kate adaptivepath.com. I magine you’re in a forest, surrounded by majestic towering trees. Underfoot is the soft, leafy, damp forest floor. Taking a seat on a fallen log, you arch the kinks out of your hunched shoulders, shake off the stress of the office and take a deep breath of fragrant, moist air. You ask yourself why work feels like you are part of a never-ending rat race...and you wonder...will it ever stop? How are you going to spearhead that major project or work with a new cross-functional team and deliver great results when the organizational environment hampers you? Much as I hate to interrupt your well-earned contemplation, I’m compelled to inform you that on the underside of the log you are sitting on is a life form teeming with insight about organizational behavior. Throughout the seemingly quiet forest, thousands of spores are performing an age-old dance, expressing quietly the tactics of surviving and thriving in this dynamic and ever-changing wooded environment. Say “hello” to slime mold. This lower fungus has evolved a clear set of survival techniques that are potent lessons for people grappling with challenges posed by shifting companies and markets. Who knew that insights into survival could be found literally under your feet? For years, biologists, botanists, media moguls, artists, authors and technologists have been captivated by the sophistication and tenacity of the slime mold lifecycle and the slime mold’s ability to morph from plant-like to animal-like behaviors in constant sync with the environment. I’m not a biologist. I’m a designer working in the field of digital products, information architecture and interaction design. But over the past eight years, I’ve been entranced with slime mold as a compelling metaphor for organizational development. In my work as an employee, manager, director and consultant, I’ve observed how organizations and teams shift in response to external forces, and I’ve found trends and patterns for acclimating and adapting to change. This article shares the examples that I’ve observed and explores possibilities and approaches for how businesses and people in them can better adapt to a rate of change that is rapidly becoming the standard for doing business. By using slime mold as a learning tool, we can identify practical tips and tools for surviving, thriving and doing great work in even the toughest of environments. This fascinating life form holds intriguing lessons for today’s knowledge worker... from sensing and responding to environments that become hostile to using the power of signals to create alignment and collective action.

Path planning is a fundamental challenge for autonomous robots, particularly in unstructured environments, where issues such as low search efficiency, suboptimal path quality, and local optima often arise. To address these challenges and enable a nonholonomic orchard robot to accomplish tasks safely and efficiently, this paper proposes a novel HPS-RRT* algorithm based on hybrid exploration and optimization mechanisms to enhance path planning performance. A hybrid sampling strategy adapted to the environmental characteristics is proposed to improve the search efficiency, and an extended step size based on Lévy distribution is designed to balance exploration and optimization. Moreover, a pruning strategy is incorporated to reduce redundant points during the search process, enhancing the efficiency of the exploration tree and reducing unnecessary expansion. Furthermore, a novel leader-based sparrow optimization algorithm is proposed to ensure that the planned path is suitable for the nonholonomic orchard robot. It can overcome the limitations of traditional smoothing methods by simultaneously optimizing curvature and path length. Compared with existing RRT*-based algorithms in environments of varying complexity, the proposed HPS-RRT* reduces the final path length by 1.7% to 27%, improves planning efficiency by 77.7% to 93.3%, and enhances path smoothness by 27.9% to 41.7%, while maintaining a 100% success rate. Furthermore, its feasibility for a nonholonomic orchard robot is validated through a multi-target planning task with curvature constraints.

This paper has investigated the technology of forwarding local wagons at railroad technical stations and established the need to improve it given the extra downtime of local wagons. The main issue relates to the considerable combinatorial complexity of the tasks of operational planning. Another problem is that as part of the conventional approach, planning a station operation and planning a local operation at it is considered separately. Another planning issue is the lack of high-quality models for the preparation of initial data, in particular, data on the duration of technological operations, such as, for example, shunting operations involving local wagons forwarding. To resolve these issues, a new approach has been proposed, under which the tasks of operative planning of a technical station’s operation and its subsystem of local operations are tackled simultaneously, based on a single model. To this end, a mathematical model of vector combinatoric optimization has been built, which uses the criteria of total operating costs and wagon-hours spent at a station when forwarding local wagon flows, in the form of separate objective functions. Within this model, a predictive model was constructed in the form of a fuzzy inference system. This model is designed to determine the duration of shunting half-runs when executing the spotting/picking operations for delivering local wagons to enterprises’ goods sheds. The model provides for the accuracy level that would suffice at planning, in contrast to classical methods. A procedure has been devised for optimizing the planning model, which employs the modern genetic algorithm of vector optimization NSGA-III. This procedure is implemented in the form of software that makes it possible to build a rational operative plan for the operation of a technical station, including a subsystem of local operations, in graphic form, thereby reducing the operating costs by 5 % and the duration of maintenance of a local wagon by 8 %. The resulting effect could reduce the turnover time of a freight car in general on the railroad network, speed up the delivery of goods, and reduce the cost of transportation

Soft robots with high degree of compliance can easily deform to delicate task settings and unstructured environments, realizing more adaptive and comfort interfaces for human-machine and human-environment. Since soft robots are made with materials with moduli similar to soft biological matters and capable of autonomous movements, scientists have been seeking insights from the nature due the excellent structural and functional capabilities. Most of the design inspiration for soft robots come from animals, such as cephalopod mollusks, because they have no rigid body structure and yet, they can perform sophisticated tasks and move around swiftly. However, very limited studies on plant-based soft robots are present, because as compared to animals, plants do not possess mobility and fast interactions with environmental changes.

When a robot manipulator performs tasks in a dynamic unstructured environment, it not only should account for where and how it should move, but also ensure that the robot can effectively avoid collisions with static and moving obstacles. Planning in absolutely unstructured and dynamic environment is much more challenging, up-to-date there is no universal solution to this problem. In this paper, we believed the concept that for motion planning in real dynamic environments, usually there is only a part of a path invalidated by obstacles, and only this part needs replanning. Thus, in this paper a practical strategy was presented for motion planning in dynamic environments. First, a variant dynamic Rapidly-exploring Random Tree (RRT) planner was designed to combine global planning with local replanning. Then, the proposed dynamic RRT algorithm was implemented under Robotic Operation System (ROS) framework and applied to a 7-degree-of-freedom manipulator. Experimental results have shown that the proposed dynamic RRT planner can plan and execute movement of robot manipulator between a starting and target position while preserving task constraints and reacting to environment changes in real time.

On-line knowledge acquisition and enhancement in robotic assembly tasks

With the rapid advancement of robotics and artificial intelligence, embodied intelligent agents operating in dynamic and unstructured environments have emerged as a key technological direction within digital twin systems. Nevertheless, their exploration capabilities in indoor digital-twin scenes remain limited. Dense semantic maps incur substantial maintenance costs and exhibit poor adaptability to dynamic environments. Furthermore, current navigation processes lack mechanisms for assessing and revisiting semantic relevance, leading to redundant exploration and inefficient resource utilization. Finally, environmental changes often result in semantic anchor degradation, with existing methods lacking effective incremental update and self-evolution mechanisms to maintain long-term consistency. To address these challenges, this paper proposes a multimodal, lightweight mapping, and revisitable self-evolving exploration agent (LRSA) for indoor digital-twin scenarios. The framework consists of three key modules: a multi-scale structured environment modeling process based on sparse semantic mapping, a large-model-driven memory-intelligence system that maintains an “area-object-feature” relational network, and a perceptual-memory self-evolution mechanism that marks inactive objects upon navigation failure and uses a memory large language model (MemoLLM) to generate and iteratively refine candidate search strategies for dynamic memory updating. Experiments conducted on the HM3D indoor dataset and the TurtleBot3 platform demonstrate that LRSA achieves a Success Rate (SR) of 55.2% and a Success weighted by Path Length (SPL) of 30.5%, surpassing state-of-the-art baselines such as ZSON, PSL, and PixNav. The proposed framework eliminates reliance on dense maps, enabling lightweight sparse modeling with reduced computational cost, synergistic memory-intelligence semantic reasoning, and self-adaptive evolution in dynamic environments. Its contributions enhance the robustness and efficiency of embodied agents’ open-world navigation and provide real-time, long-term semantic updating for urban digital twin systems, supporting autonomous “self-perception, self-evolution, and self-maintenance.”