Category Archives: Robotics

Hierarchical RL with diverse methods integrated in the framework

Ye Zhou, Hann Woei Ho, Online robot guidance and navigation in non-stationary environment with hybrid Hierarchical Reinforcement Learning, Engineering Applications of Artificial Intelligence, Volume 114, 2022 DOI: 10.1016/j.engappai.2022.105152.

Hierarchical Reinforcement Learning (HRL) provides an option to solve complex guidance and navigation problems with high-dimensional spaces, multiple objectives, and a large number of states and actions. The current HRL methods often use the same or similar reinforcement learning methods within one application so that multiple objectives can be easily combined. Since there is not a single learning method that can benefit all targets, hybrid Hierarchical Reinforcement Learning (hHRL) was proposed to use various methods to optimize the learning with different types of information and objectives in one application. The previous hHRL method, however, requires manual task-specific designs, which involves engineers\u2019 preferences and may impede its transfer learning ability. This paper, therefore, proposes a systematic online guidance and navigation method under the framework of hHRL, which generalizes training samples with a function approximator, decomposes the state space automatically, and thus does not require task-specific designs. The simulation results indicate that the proposed method is superior to the previous hHRL method, which requires manual decomposition, in terms of the convergence rate and the learnt policy. It is also shown that this method is generally applicable to non-stationary environments changing over episodes and over time without the loss of efficiency even with noisy state information.

Human+machine sequential decision making

Q. Zhang, Y. Kang, Y. -B. Zhao, P. Li and S. You, Traded Control of Human\u2013Machine Systems for Sequential Decision-Making Based on Reinforcement Learning, IEEE Transactions on Artificial Intelligence, vol. 3, no. 4, pp. 553-566, Aug. 2022 DOI: 10.1109/TAI.2021.3127857.

Sequential decision-making (SDM) is a common type of decision-making problem with sequential and multistage characteristics. Among them, the learning and updating of policy are the main challenges in solving SDM problems. Unlike previous machine autonomy driven by artificial intelligence alone, we improve the control performance of SDM tasks by combining human intelligence and machine intelligence. Specifically, this article presents a paradigm of a human\u2013machine traded control systems based on reinforcement learning methods to optimize the solution process of sequential decision problems. By designing the idea of autonomous boundary and credibility assessment, we enable humans and machines at the decision-making level of the systems to collaborate more effectively. And the arbitration in the human\u2013machine traded control systems introduces the Bayesian neural network and the dropout mechanism to consider the uncertainty and security constraints. Finally, experiments involving machine traded control, human traded control were implemented. The preliminary experimental results of this article show that our traded control method improves decision-making performance and verifies the effectiveness for SDM problems.

New algorithms for optimal path planning with certain optimality guarantees

Strub MP, Gammell JD. Adaptively Informed Trees (AIT*) and Effort Informed Trees (EIT*): Asymmetric bidirectional sampling-based path planning, The International Journal of Robotics Research. 2022;41(4):390-417 DOI: 10.1177/02783649211069572.

Optimal path planning is the problem of finding a valid sequence of states between a start and goal that optimizes an objective. Informed path planning algorithms order their search with problem-specific knowledge expressed as heuristics and can be orders of magnitude more efficient than uninformed algorithms. Heuristics are most effective when they are both accurate and computationally inexpensive to evaluate, but these are often conflicting characteristics. This makes the selection of appropriate heuristics difficult for many problems. This paper presents two almost-surely asymptotically optimal sampling-based path planning algorithms to address this challenge, Adaptively Informed Trees (AIT*) and Effort Informed Trees (EIT*). These algorithms use an asymmetric bidirectional search in which both searches continuously inform each other. This allows AIT* and EIT* to improve planning performance by simultaneously calculating and exploiting increasingly accurate, problem-specific heuristics. The benefits of AIT* and EIT* relative to other sampling-based algorithms are demonstrated on 12 problems in abstract, robotic, and biomedical domains optimizing path length and obstacle clearance. The experiments show that AIT* and EIT* outperform other algorithms on problems optimizing obstacle clearance, where a priori cost heuristics are often ineffective, and still perform well on problems minimizing path length, where such heuristics are often effective.

Probabilistic ICP (Iterative Closest Point) with an intro on classical ICP

Breux Y, Mas A, Lapierre L. On-manifold probabilistic Iterative Closest Point: Application to underwater karst exploration, The International Journal of Robotics Research. 2022;41(9-10):875-902 DOI: 10.1177/02783649221101418.

This paper proposes MpIC, an on-manifold derivation of the probabilistic Iterative Correspondence (pIC) algorithm, which is a stochastic version of the original Iterative Closest Point. It is developed in the context of autonomous underwater karst exploration based on acoustic sonars. First, a derivation of pIC based on the Lie group structure of SE(3) is developed. The closed-form expression of the covariance modeling the estimated rigid transformation is also provided. In a second part, its application to 3D scan matching between acoustic sonar measurements is proposed. It is a prolongation of previous work on elevation angle estimation from wide-beam acoustic sonar. While the pIC approach proposed is intended to be a key component in a Simultaneous Localization and Mapping framework, this paper focuses on assessing its viability on a unitary basis. As ground truth data in karst aquifer are difficult to obtain, quantitative experiments are carried out on a simulated karst environment and show improvement compared to previous state-of-the-art approach. The algorithm is also evaluated on a real underwater cave dataset demonstrating its practical applicability.

See also: Maken FA, Ramos F, Ott L. Bayesian iterative closest point for mobile robot localization. The International Journal of Robotics Research. 2022;41(9-10):851-874. doi:10.1177/02783649221101417

Survey of machine learning applied to robot navigation, including a brief survey of classic navigation

Xiao, X., Liu, B., Warnell, G. et al. Motion planning and control for mobile robot navigation using machine learning: a survey, Auton Robot 46, 569\u2013597 (2022) DOI: 10.1007/s10514-022-10039-8.

Moving in complex environments is an essential capability of intelligent mobile robots. Decades of research and engineering have been dedicated to developing sophisticated navigation systems to move mobile robots from one point to another. Despite their overall success, a recently emerging research thrust is devoted to developing machine learning techniques to address the same problem, based in large part on the success of deep learning. However, to date, there has not been much direct comparison between the classical and emerging paradigms to this problem. In this article, we survey recent works that apply machine learning for motion planning and control in mobile robot navigation, within the context of classical navigation systems. The surveyed works are classified into different categories, which delineate the relationship of the learning approaches to classical methods. Based on this classification, we identify common challenges and promising future directions.

POMDP Planner that uses multiple levels of approximation to the system dynamics to reduce the number and complexity of forward simulations

Hoerger M, Kurniawati H, Elfes A. , Multilevel Monte Carlo for solving POMDPs on-line, The International Journal of Robotics Research. 2023;42(4-5):196-213 DOI: 10.1177/02783649221093658.

Planning under partial observability is essential for autonomous robots. A principled way to address such planning problems is the Partially Observable Markov Decision Process (POMDP). Although solving POMDPs is computationally intractable, substantial advancements have been achieved in developing approximate POMDP solvers in the past two decades. However, computing robust solutions for systems with complex dynamics remains challenging. Most on-line solvers rely on a large number of forward simulations and standard Monte Carlo methods to compute the expected outcomes of actions the robot can perform. For systems with complex dynamics, for example, those with non-linear dynamics that admit no closed-form solution, even a single forward simulation can be prohibitively expensive. Of course, this issue exacerbates for problems with long planning horizons. This paper aims to alleviate the above difficulty. To this end, we propose a new on-line POMDP solver, called Multilevel POMDP Planner\u2009(MLPP), that combines the commonly known Monte-Carlo-Tree-Search with the concept of Multilevel Monte Carlo to speed up our capability in generating approximately optimal solutions for POMDPs with complex dynamics. Experiments on four different problems involving torque control, navigation and grasping indicate that MLPP\u2009substantially outperforms state-of-the-art POMDP solvers.

A survey on visual SLAM in robotics

Iman Abaspur Kazerouni, Luke Fitzgerald, Gerard Dooly, Daniel Toal, A survey of state-of-the-art on visual SLAM, Expert Systems with Applications, Volume 205, 2022 DOI: 10.1016/j.eswa.2022.117734.

This paper is an overview to Visual Simultaneous Localization and Mapping (V-SLAM). We discuss the basic definitions in the SLAM and vision system fields and provide a review of the state-of-the-art methods utilized for mobile robot\u2019s vision and SLAM. This paper covers topics from the basic SLAM methods, vision sensors, machine vision algorithms for feature extraction and matching, Deep Learning (DL) methods and datasets for Visual Odometry (VO) and Loop Closure (LC) in V-SLAM applications. Several feature extraction and matching algorithms are simulated to show a better vision of feature-based techniques.

See also:

Jun Cheng, Liyan Zhang, Qihong Chen, Xinrong Hu, Jingcao Cai, “A review of visual SLAM methods for autonomous driving vehicles,” Engineering Applications of Artificial Intelligence, Volume 114, 2022, 104992, ISSN 0952-1976, https://doi.org/10.1016/j.engappai.2022.104992.

Tianyao Zhang, Xiaoguang Hu, Jin Xiao, Guofeng Zhang, “A survey of visual navigation: From geometry to embodied AI,” Engineering Applications of Artificial Intelligence, Volume 114, 2022, 105036, ISSN 0952-1976, https://doi.org/10.1016/j.engappai.2022.105036.

Kalman filter with time delays

H. Zhu, J. Mi, Y. Li, K. -V. Yuen and H. Leung, VB-Kalman Based Localization for Connected Vehicles With Delayed and Lost Measurements: Theory and Experiments, EEE/ASME Transactions on Mechatronics, vol. 27, no. 3, pp. 1370-1378, June 2022 DOI: 10.1109/TMECH.2021.3095096.

Traditionally, connected vehicles (CVs) share their own sensor data that relies on the satellite with their surrounding vehicles by vehicle-to-vehicle (V2V) communication. However, the satellite-based signal sometimes may be lost due to environmental factors. Time-delays and packet dropouts may occur randomly by V2V communication. To ensure the reliability and accuracy of localization for CVs, a novel variational Bayesian (VB)-Kalman method is developed for unknown and time varying probabilities of delayed and lost measurements. In this VB-Kalman localization method, two random variables are introduced to indicate whether a measurement is delayed and available, respectively. A hierarchical model is then formulated and its parameters and state are simultaneously estimated by the VB technique. Experimental results validate the proposed method for the localization of CVs in practice.

NOTE: See also S. Guo, Y. Liu, Y. Zheng and T. Ersal, “A Delay Compensation Framework for Connected Testbeds,” in IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 52, no. 7, pp. 4163-4176, July 2022, doi: 10.1109/TSMC.2021.3091974.

A tutorial on the integration of ROS with some interesting software, such as Jupyter

T. Fischer, W. Vollprecht, S. Traversaro, S. Yen, C. Herrero and M. Milford, A RoboStack Tutorial: Using the Robot Operating System Alongside the Conda and Jupyter Data Science Ecosystems, IEEE Robotics & Automation Magazine, vol. 29, no. 2, pp. 65-74, June 2022 DOI: 10.1109/MRA.2021.3128367.

The Robot Operating System (ROS) has become the de facto standard middleware in the robotics community [1] . ROS bundles everything, from low-level drivers to tools that transform among coordinate systems, to state-of-the-art perception and control algorithms. One of ROS\u2019s key merits is the rich ecosystem of standardized tools to build and distribute ROS-based software.

Reconstructing indoor map layouts from geometrical data

Matteo Luperto, Francesco Amigoni, Reconstruction and prediction of the layout of indoor environments from two-dimensional metric maps, Engineering Applications of Artificial Intelligence, Volume 113, 2022 DOI: 10.1016/j.engappai.2022.104910.

Metric maps, like occupancy grids, are one of the most common ways to represent indoor environments in autonomous mobile robotics. Although they are effective for navigation and localization, metric maps contain little knowledge about the structure of the buildings they represent. In this paper, we propose a method that identifies the structure of indoor environments from 2D metric maps by retrieving their layout, namely an abstract geometrical representation that models walls as line segments and rooms as polygons. The method works by finding regularities within a building, abstracting from the possibly noisy information of the metric map, and uses such knowledge to reconstruct the layout of the observed part and to predict a possible layout of the partially observed portion of the building. Thus, differently of other methods from the state of the art, our method can be applied both to fully observed environments and, most significantly, to partially observed ones. Experimental results show that our approach performs effectively and robustly on different types of input metric maps and that the predicted layout is increasingly more accurate when the input metric map is increasingly more complete. The layout returned by our method can be exploited in several tasks, such as semantic mapping, place categorization, path planning, human\u2013robot communication, and task allocation.