Precise landing of Unmanned Aerial Vehicles (UAVs) onto moving platforms like Autonomous Surface Vehicles (ASVs) is both important and challenging, especially in GPS-denied environments, for collaborative navigation of heterogeneous vehicles. UAVs need to land within a confined space onboard ASV to get energy replenishment, while ASV is subject to translational and rotational disturbances due to wind and water flow. Current solutions either rely on high-level waypoint navigation, which struggles to robustly land on varied-speed targets, or necessitate laborious manual tuning of controller parameters, and expensive sensors for target localization. Therefore, we propose an adaptive velocity control algorithm that leverages Particle Swarm Optimization (PSO) and Neural Network (NN) to optimize PID parameters across varying flight altitudes and distinct speeds of a moving boat. The cost function of PSO includes the status change rates of UAV and proximity to the target. The NN further interpolates the PSO-founded PID parameters. The proposed method implemented on a water strider hexacopter design, not only ensures accuracy but also increases robustness. Moreover, this NN-PSO can be readily adapted to suit various mission requirements. Its ability to achieve precise landings extends its applicability to scenarios, including but not limited to rescue missions, package deliveries, and workspace inspections.

Offline pretraining with a static dataset followed by online fine-tuning (offline-to-online, or OtO) is a paradigm that is well matched to a real-world RL deployment process: in few real settings would one deploy an offline policy with no test runs and tuning. In this scenario, we aim to find the best-performing policy within a limited budget of online interactions. Previous work in the OtO setting has focused on correcting for bias introduced by the policy-constraint mechanisms of offline RL algorithms. Such constraints keep the learned policy close to the behavior policy that collected the dataset, but this unnecessarily limits policy performance if the behavior policy is far from optimal. Instead, we forgo policy constraints and frame OtO RL as an exploration problem: we must maximize the benefit of the online data-collection. We study major online RL exploration paradigms, adapting them to work well with the OtO setting. These adapted methods contribute several strong baselines. Also, we introduce an algorithm for planning to go out of distribution (PTGOOD), which targets online exploration in relatively high-reward regions of the state-action space unlikely to be visited by the behavior policy. By leveraging concepts from the Conditional Entropy Bottleneck, PTGOOD encourages data collected online to provide new information relevant to improving the final deployment policy. In that way the limited interaction budget is used effectively. We show that PTGOOD significantly improves agent returns during online fine-tuning and finds the optimal policy in as few as 10k online steps in Walker and in as few as 50k in complex control tasks like Humanoid. Also, we find that PTGOOD avoids the suboptimal policy convergence that many of our baselines exhibit in several environments.

The objective is to find the optimal state vector that minimizes the measurement error between the estimated pose and environmental landmarks. Most SLAM algorithms are passive, i.e., the robot is controlled manually and the navigation or path planning algorithm does not actively take part in robot motion or trajectory. Active SLAM (A-SLAM), however, tries to solve the optimal exploration problem of the unknown environment by proposing a navigation strategy that generates future goal/target positions actions which decrease map and pose uncertainties, thus enabling a fully autonomous navigation and mapping SLAM system without the need of an external controller or human effort. In Active Collaborative SLAM (AC-SLAM) multiple robots interchange information to improve their localization estimation and map accuracy to achieve some high-level tasks such as exploration. The exchanged information can be localization information [1], entropy [2], visual features [3], and frontier points [4]. In this article, we present a multi-agent AC-SLAM system for efficient environment exploration using frontiers detected over an Occupancy Grid (OG) map. In particular, in this work, we aim at: 1. Extending the A-SLAM approach of [5] which uses a computationally inexpensive D-optimality criterion for utility computation to a multi-agent AC-SLAM framework.

Executing time-sensitive multi-robot missions involves two distinct problems: Multi-Robot Task Assignment (MRTA) and Multi-Agent Path Finding (MAPF). Computing safe paths that complete every task and minimize the time to mission completion, or makespan, is a significant computational challenge even for small teams. In many missions, tasks can be generated during execution which is typically handled by either recomputing task assignments and paths from scratch, or by modifying existing plans using approximate approaches. While performing task reassignment and path finding from scratch produces theoretically optimal results, the computational load makes it too expensive for online implementation. In this work, we present Time-Sensitive Online Task Assignment and Navigation (TSOTAN), a framework which can quickly incorporate online generated tasks while guaranteeing bounded suboptimal task assignment makespans. It does this by assessing the quality of partial task reassignments and only performing a complete reoptimization when the makespan exceeds a user specified suboptimality bound. Through experiments in 2D environments we demonstrate TSOTAN's ability to produce quality solutions with computation times suitable for online implementation.

This article presents a comprehensive review of control algorithms used in mobile robotics, a field in constant evolution. Mobile robotics has seen significant advances in recent years, driven by the demand for applications in various sectors, such as industrial automation, space exploration, and medical care. The review focuses on control algorithms that address specific challenges in navigation, localization, mapping, and path planning in changing and unknown environments. Classical approaches, such as PID control and methods based on classical control theory, as well as modern techniques, including deep learning and model-based planning, are discussed in detail. In addition, practical applications and remaining challenges in implementing these algorithms in real-world mobile robots are highlighted. Ultimately, this review provides a comprehensive overview of the diversity and complexity of control algorithms in mobile robotics, helping researchers and practitioners to better understand the options available to address specific problems in this exciting area of study.

Recent efforts have augmented language models (LMs) with external tools or environments, leading to the development of language agents that can reason and act. However, most of these agents rely on few-shot prompting techniques with off-the-shelf LMs. In this paper, we investigate and argue for the overlooked direction of fine-tuning LMs to obtain language agents. Using a setup of question answering (QA) with a Google search API, we explore a variety of base LMs, prompting methods, fine-tuning data, and QA tasks, and find language agents are consistently improved after fine-tuning their backbone LMs. For example, fine-tuning Llama2-7B with 500 agent trajectories generated by GPT-4 leads to a 77% HotpotQA performance increase. Furthermore, we propose FireAct, a novel approach to fine-tuning LMs with trajectories from multiple tasks and prompting methods, and show having more diverse fine-tuning data can further improve agents. Along with other findings regarding scaling effects, robustness, generalization, efficiency and cost, our work establishes comprehensive benefits of fine-tuning LMs for agents, and provides an initial set of experimental designs, insights, as well as open questions toward language agent fine-tuning.

Motion prediction and cost evaluation are vital components in the decision-making system of autonomous vehicles. However, existing methods often ignore the importance of cost learning and treat them as separate modules. In this study, we employ a tree-structured policy planner and propose a differentiable joint training framework for both ego-conditioned prediction and cost models, resulting in a direct improvement of the final planning performance. For conditional prediction, we introduce a query-centric Transformer model that performs efficient ego-conditioned motion prediction. For planning cost, we propose a learnable context-aware cost function with latent interaction features, facilitating differentiable joint learning. We validate our proposed approach using the real-world nuPlan dataset and its associated planning test platform. Our framework not only matches state-of-the-art planning methods but outperforms other learning-based methods in planning quality, while operating more efficiently in terms of runtime. We show that joint training delivers significantly better performance than separate training of the two modules. Additionally, we find that tree-structured policy planning outperforms the conventional single-stage planning approach.

As artificial intelligence (AI) research reaches new peaks, more and more AI systems are being implemented, applied, and deployed worldwide. Further integration of such systems with human societies demands a thorough consideration of their consequences and effects. The inherent property of most, if not all, AI systems is to act with an unprecedented level of autonomy, often in settings where its actions might directly affect human beings. The growing field of Value Alignment (VA) aims to explicitly study the values pursued and exhibited by AI agents and make sure that they correspond to human values. Motivating examples of VA often consider the long-term and potentially existential threats posed by powerful, superintelligent AI agents with misaligned values [Russell, 2022a]. Not less pertinent are the short-term threats of more mundane, highly specialized AI systems, employed in particular in control settings, becoming misaligned. A prominent case where a potential misalignment is particularly dangerous is given by systems where humans voluntarily cede control of a system to algorithms. Examples of such systems abound: self-driving cars, where the driver cedes control of their vehicle [Haboucha et al., 2017]; recommender systems and content algorithms [Carissimo et al., 2023], where the user cedes some control over their access to information; traffic control systems, where drivers cede control of traffic flow coordination [Korecki and Helbing, 2022], are all examples of systems where AI is a control method of choice or is in the process of becoming one

At the operational level, drivers can freely accept or decline trip requests that can significantly impact system performance in terms of travellers' waiting time, drivers' idle time and income. Despite the extensive research into the supply-side operations, the behavioural aspects, particularly drivers' ride acceptance behaviour remains so far largely unknown. To this end, we reproduce the dynamics of a two-sided mobility platform on the road network of Delft using an agent-based simulator. Then, we implement a ride acceptance decision model enabling drivers to apply their acceptance strategies. Our findings reveal that drivers who follow the decision model, on average, earn higher income compared to drivers who randomly accept trip requests. The overall income equality between drivers with the acceptance decision is higher and travellers experience lower waiting time in this setting.

Visual place recognition (VPR) capabilities enable autonomous robots to navigate complex environments by discovering the environment's topology based on visual input. Most research efforts focus on enhancing the accuracy and robustness of single-robot VPR but often encounter issues such as occlusion due to individual viewpoints. Despite a number of research on multi-robot metric-based localization, there is a notable gap in research concerning more robust and efficient place-based localization with a multi-robot system. This work proposes collaborative VPR, where multiple robots share abstracted visual features to enhance place recognition capabilities. We also introduce a novel collaborative VPR framework based on similarity-regularized information fusion, reducing irrelevant noise while harnessing valuable data from collaborators. This framework seamlessly integrates with well-established single-robot VPR techniques and supports end-to-end training with a weakly-supervised contrastive loss. We conduct experiments in urban, rural, and indoor scenes, achieving a notable improvement over single-agent VPR in urban environments (~12\%), along with consistent enhancements in rural (~3\%) and indoor (~1\%) scenarios. Our work presents a promising solution to the pressing challenges of VPR, representing a substantial step towards safe and robust autonomous systems.