Utilizing robots for autonomous target search in complex and unknown environments can greatly improve the efficiency of search and rescue missions. However, existing methods have shown inadequate performance due to hardware platform limitations, inefficient viewpoint selection strategies, and conservative motion planning. In this work, we propose HEATS, which enhances the search capability of mobile manipulators in complex and unknown environments. We design a target viewpoint planner tailored to the strengths of mobile manipulators, ensuring efficient and comprehensive viewpoint planning. Supported by this, a whole-body motion planner integrates global path search with local IPC optimization, enabling the mobile manipulator to safely and agilely visit target viewpoints, significantly improving search performance. We present extensive simulated and real-world tests, in which our method demonstrates reduced search time, higher target search completeness, and lower movement cost compared to classic and state-of-the-art approaches. Our method will be open-sourced for community benefit.

Abstract-- To work in unknown outdoor environments, autonomous sampling machines need the ability to target samples despite limited visibility and robotic arm reach distance. We design a heuristic guided search method to speed up the search process and more efficiently localize the approximate center of soil regions. Through simulation experiments, we assess the effectiveness of the proposed algorithm and discover superior performance in terms of speed, distance traveled, and success rate compared to naive baselines. I. INTRODUCTION In this paper, we address the problem of autonomous sample collection in outdoor, unknown environments. While Figure 1: In this example, a robot--perhaps a camera mounted collecting soil or similar organic material, there are no end effector of a robotic arm--uses a heuristic method to guarantees that samples will be reachable, visible, or even search for the center of a soil region in a sample distribution. For this reason, a robot needs an effective search task The circle is the start position, and the star indicates the to locate and move sufficiently close to the samples prior to center which the agent aims to reach.

This paper addresses the problem of target search and tracking using a fleet of cooperating UAVs evolving in some unknown region of interest containing an a priori unknown number of moving ground targets. Each drone is equipped with an embedded Computer Vision System (CVS), providing an image with labeled pixels and a depth map of the observed part of its environment. Moreover, a box containing the corresponding pixels in the image frame is available when a UAV identifies a target. Hypotheses regarding information provided by the pixel classification, depth map construction, and target identification algorithms are proposed to allow its exploitation by set-membership approaches. A set-membership target location estimator is developed using the information provided by the CVS. Each UAV evaluates sets guaranteed to contain the location of the identified targets and a set possibly containing the locations of targets still to be identified. Then, each UAV uses these sets to search and track targets cooperatively.

Equipping drones with target search capabilities is highly desirable for applications in disaster rescue and smart warehouse delivery systems. Multiple intelligent drones that can collaborate with each other and maneuver among obstacles show more effectiveness in accomplishing tasks in a shorter amount of time. However, carrying out collaborative target search (CTS) without prior target information is extremely challenging, especially with a visual drone swarm. In this work, we propose a novel data-efficient deep reinforcement learning (DRL) approach called adaptive curriculum embedded multistage learning (ACEMSL) to address these challenges, mainly 3-D sparse reward space exploration with limited visual perception and collaborative behavior requirements. Specifically, we decompose the CTS task into several subtasks including individual obstacle avoidance, target search, and inter-agent collaboration, and progressively train the agents with multistage learning. Meanwhile, an adaptive embedded curriculum (AEC) is designed, where the task difficulty level (TDL) can be adaptively adjusted based on the success rate (SR) achieved in training. ACEMSL allows data-efficient training and individual-team reward allocation for the visual drone swarm. Furthermore, we deploy the trained model over a real visual drone swarm and perform CTS operations without fine-tuning. Extensive simulations and real-world flight tests validate the effectiveness and generalizability of ACEMSL. The project is available at https://github.com/NTU-UAVG/CTS-visual-drone-swarm.git.

In recent years, the demand for service robots capable of executing tasks beyond autonomous navigation has grown. In the future, service robots will be expected to perform complex tasks like 'Set table for dinner'. High-level tasks like these, require, among other capabilities, the ability to retrieve multiple targets. This paper delves into the challenge of locating multiple targets in an environment, termed 'Find my Objects.' We present a novel heuristic designed to facilitate robots in conducting a preferential search for multiple targets in indoor spaces. Our approach involves a Semantic SLAM framework that combines semantic object recognition with geometric data to generate a multi-layered map. We fuse the semantic maps with probabilistic priors for efficient inferencing. Recognizing the challenges introduced by obstacles that might obscure a navigation goal and render standard point-to-point navigation strategies less viable, our methodology offers resilience to such factors. Importantly, our method is adaptable to various object detectors, RGB-D SLAM techniques, and local navigation planners. We demonstrate the 'Find my Objects' task in real-world indoor environments, yielding quantitative results that attest to the effectiveness of our methodology. This strategy can be applied in scenarios where service robots need to locate, grasp, and transport objects, taking into account user preferences. For a brief summary, please refer to our video: https://tinyurl.com/PrefTargetSearch

Active target sensing is the task of discovering and classifying an unknown number of targets in an environment and is critical in search-and-rescue missions. This paper develops a deep reinforcement learning approach to plan informative trajectories that increase the likelihood for an uncrewed aerial vehicle (UAV) to discover missing targets. Our approach efficiently (1) explores the environment to discover new targets, (2) exploits its current belief of the target states and incorporates inaccurate sensor models for high-fidelity classification, and (3) generates dynamically feasible trajectories for an agile UAV by employing a motion primitive library. Extensive simulations on randomly generated environments show that our approach is more efficient in discovering and classifying targets than several other baselines. A unique characteristic of our approach, in contrast to heuristic informative path planning approaches, is that it is robust to varying amounts of deviations of the prior belief from the true target distribution, thereby alleviating the challenge of designing heuristics specific to the application conditions.

This work develops novel strategies for optimal planning with semantic observations using continuous state Partially Observable Markov Decision Processes (CPOMDPs). Two major innovations are presented in relation to Gaussian mixture (GM) CPOMDP policy approximation methods. While existing methods have many theoretically nice properties, they are hampered by the inability to efficiently represent and reason over hybrid continuous-discrete probabilistic models. The first major innovation is the derivation of closed-form variational Bayes GM approximations of Point-Based Value Iteration Bellman policy backups, using softmax models of continuous-discrete semantic observation probabilities. A key benefit of this approach is that dynamic decision-making tasks can be performed with complex non-Gaussian uncertainties, while also exploiting continuous dynamic state space models (thus avoiding cumbersome and costly discretization). The second major innovation is a new clustering-based technique for mixture condensation that scales well to very large GM policy functions and belief functions. Simulation results for a target search and interception task with semantic observations show that the GM policies resulting from these innovations are more effective than those produced by other state of the art GM and Monte Carlo based policy approximations, but require significantly less modeling overhead and runtime cost. Additional results demonstrate the robustness of this approach to model errors.

In search applications, autonomous unmanned vehicles must be able to efficiently reacquire and localize mobile targets that can remain out of view for long periods of time in large spaces. As such, all available information sources must be actively leveraged -- including imprecise but readily available semantic observations provided by humans. To achieve this, this work develops and validates a novel collaborative human-machine sensing solution for dynamic target search. Our approach uses continuous partially observable Markov decision process (CPOMDP) planning to generate vehicle trajectories that optimally exploit imperfect detection data from onboard sensors, as well as semantic natural language observations that can be specifically requested from human sensors. The key innovation is a scalable hierarchical Gaussian mixture model formulation for efficiently solving CPOMDPs with semantic observations in continuous dynamic state spaces. The approach is demonstrated and validated with a real human-robot team engaged in dynamic indoor target search and capture scenarios on a custom testbed.

Moving Target Search (MTS) is a dynamic path planning problem, where an agent is trying to reach a moving entity with a minimum path cost. Problems of this nature can be found in video games and dynamic robotics, which require fast processing time (real time). In this work, we introduce a new algorithm for this problem - the Moving Target Search with Subgoal Graphs (MTSub). MTSub is based on environment abstraction and uses Subgoal Graphs to speed up the searches for a minimal cost route to the target. The algorithm is optimal with respect to the knowledge that the agent has during the search. Experimental results show that MTSub can be used in real-time applications (e.g., applications requiring 5 microseconds response time per step). The experiments compared MTSub to G-FRA*, which is the best known dynamic algorithm so far, showing that MTSub is up to 29 times faster in average time per step, and up to 186 times faster in maximum time per step.

Incremental search algorithms reuse information from previous searches to speed up the current search and are thus often able to find shortest paths for series of similar search problems faster than by solving each search problem independently from scratch. However, they do poorly on moving target search problems, where both the start and goal cells change over time. In this paper, we thus develop Fringe-Retrieving A* (FRA*), an incremental version of A* that repeatedly finds shortest paths for moving target search in known gridworlds. We demonstrate experimentally that it runs up to one order of magnitude faster than a variety of state-of-the-art incremental search algorithms applied to moving target search in known gridworlds.