Defected twisted ring topology for autonomous periodic flip-spin-orbit soft robot

Periodic spin-orbit motion is ubiquitous in nature, observed from electrons orbiting nuclei to spinning planets orbiting the Sun. Achieving autonomous periodic orbiting motions, along circular and noncircular paths, in soft mobile robotics is crucial for adaptive and intelligent exploration of unknown environments-a grand challenge yet to be accomplished. Here, we report leveraging a closed-loop twisted ring topology with a defect for an autonomous soft robot capable of achieving periodic spin-orbiting motions with programmed circular and re-programmed irregular-shaped trajectories. Constructed by bonding a twisted liquid crystal elastomer ribbon into a closed-loop ring topology, the robot exhibits three coupled periodic self-motions in response to constant temperature or constant light sources: inside-out flipping, self-spinning around the ring center, and self-orbiting around a point outside the ring. The coupled spinning and orbiting motions share the same direction and period. The spinning or orbiting direction depends on the twisting chirality, while the orbital radius and period are determined by the twisted ring geometry and thermal actuation. The flip-spin and orbiting motions arise from the twisted ring topology and a bonding site defect that breaks the force symmetry, respectively. By utilizing the twisting-encoded autonomous flip-spin-orbit motions, we showcase the robot's potential for intelligently mapping the geometric boundaries of unknown confined spaces, including convex shapes like circles, squares, triangles, and pentagons and concaves shapes with multi-robots, as well as health monitoring of unknown confined spaces with boundary damages.

A Review on Visual-SLAM: Advancements from Geometric Modelling to Learning-Based Semantic Scene Understanding Using Multi-Modal Sensor Fusion

Simultaneous Localisation and Mapping (SLAM) is one of the fundamental problems in autonomous mobile robots where a robot needs to reconstruct a previously unseen environment while simultaneously localising itself with respect to the map. In particular, Visual-SLAM uses various sensors from the mobile robot for collecting and sensing a representation of the map. Traditionally, geometric model-based techniques were used to tackle the SLAM problem, which tends to be error-prone under challenging environments. Recent advancements in computer vision, such as deep learning techniques, have provided a data-driven approach to tackle the Visual-SLAM problem. This review summarises recent advancements in the Visual-SLAM domain using various learning-based methods. We begin by providing a concise overview of the geometric model-based approaches, followed by technical reviews on the current paradigms in SLAM. Then, we present the various learning-based approaches to collecting sensory inputs from mobile robots and performing scene understanding. The current paradigms in deep-learning-based semantic understanding are discussed and placed under the context of Visual-SLAM. Finally, we discuss challenges and further opportunities in the direction of learning-based approaches in Visual-SLAM.

Active Mapping and Robot Exploration: A Survey

Simultaneous localization and mapping responds to the problem of building a map of the environment without any prior information and based on the data obtained from one or more sensors. In most situations, the robot is driven by a human operator, but some systems are capable of navigating autonomously while mapping, which is called native simultaneous localization and mapping. This strategy focuses on actively calculating the trajectories to explore the environment while building a map with a minimum error. In this paper, a comprehensive review of the research work developed in this field is provided, targeting the most relevant contributions in indoor mobile robotics.

A Deep Reinforcement Learning Approach for Active SLAM

In this paper, we formulate the active SLAM paradigm in terms of model-free Deep Reinforcement Learning, embedding the traditional utility functions based on the Theory of Optimal Experimental Design in rewards, and therefore relaxing the intensive computations of classical approaches. We validate such formulation in a complex simulation environment, using a state-of-the-art deep Q-learning architecture with laser measurements as network inputs. Trained agents become capable not only to learn a policy to navigate and explore in the absence of an environment model but also to transfer their knowledge to previously unseen maps, which is a key requirement in robotic exploration.

Search and rescue under the forest canopy using multiple UAVs

We present a multi-robot system for GPS-denied search and rescue under the forest canopy. Forests are particularly challenging environments for collaborative exploration and mapping, in large part due to the existence of severe perceptual aliasing which hinders reliable loop closure detection for mutual localization and map fusion. Our proposed system features unmanned aerial vehicles (UAVs) that perform onboard sensing, estimation, and planning. When communication is available, each UAV transmits compressed tree-based submaps to a central ground station for collaborative simultaneous localization and mapping (CSLAM). To overcome high measurement noise and perceptual aliasing, we use the local configuration of a group of trees as a distinctive feature for robust loop closure detection. Furthermore, we propose a novel procedure based on cycle consistent multiway matching to recover from incorrect pairwise data associations. The returned global data association is guaranteed to be cycle consistent, and is shown to improve both precision and recall compared with the input pairwise associations. The proposed multi-UAV system is validated both in simulation and during real-world collaborative exploration missions at NASA Langley Research Center.

Mobile Robot Path Planning Using a Laser Range Finder for Environments with Transparent Obstacles

Environment maps must first be generated to drive mobile robots automatically. Path planning is performed based on the information given in an environment map. Various types of sensors, such as ultrasonic and laser sensors, are used by mobile robots to acquire data on its surrounding environment. Among these, the laser sensor, which has the property of being able to go straight and high accuracy, is used most often. However, the beams from laser sensors are refracted and reflected when it meets a transparent obstacle, thus generating noise. Therefore, in this paper, a state-of-the-art algorithm was proposed to detect transparent obstacles by analyzing the pattern of the reflected noise generated when a laser meets a transparent obstacle. The experiment was carried out using the environment map generated by the aforementioned method and gave results demonstrating that the robot could avoid transparent obstacles while it was moving towards the destination.

A high-efficiency, information-based exploration path planning method for active simultaneous localization and mapping

The efficiency of exploration in an unknown scene and full coverage of the scene are essential for a robot to complete simultaneous localization and mapping actively. However, it is challenging for a robot to explore an unknown environment with high efficiency and full coverage autonomously. In this article, we propose a novel exploration path planning method based on information entropy. An information entropy map is first constructed, and its boundary features are extracted. Then a Dijkstra-based algorithm is applied to generate candidate exploration paths based on the boundary features. The dead-reckoning algorithm is used to predict the uncertainty of the robot’s pose along each candidate path. The exploration path is selected based on exploration efficiency and/or high coverage. Simulations and experiments are conducted to evaluate the proposed method’s effectiveness. The results demonstrated that the proposed method achieved not only higher exploration efficiency but also a larger coverage area.

Active SLAM for Autonomous Underwater Exploration

Exploration of a complex underwater environment without an a priori map is beyond the state of the art for autonomous underwater vehicles (AUVs). Despite several efforts regarding simultaneous localization and mapping (SLAM) and view planning, there is no exploration framework, tailored to underwater vehicles, that faces exploration combining mapping, active localization, and view planning in a unified way. We propose an exploration framework, based on an active SLAM strategy, that combines three main elements: a view planner, an iterative closest point algorithm (ICP)-based pose-graph SLAM algorithm, and an action selection mechanism that makes use of the joint map and state entropy reduction. To demonstrate the benefits of the active SLAM strategy, several tests were conducted with the Girona 500 AUV, both in simulation and in the real world. The article shows how the proposed framework makes it possible to plan exploratory trajectories that keep the vehicle’s uncertainty bounded; thus, creating more consistent maps.

Ergodic Exploration Using Binary Sensing for Nonparametric Shape Estimation

Current methods to estimate object shape-using either vision or touch-generally depend on high-resolution sensing. Here, we exploit ergodic exploration to demonstrate successful shape estimation when using a low-resolution binary contact sensor. The measurement model is posed as a collision-based tactile measurement, and classification methods are used to discriminate between shape boundary regions in the search space. Posterior likelihood estimates of the measurement model help the system actively seek out regions where the binary sensor is most likely to return informative measurements. Results show successful shape estimation of various objects as well as the ability to identify multiple objects in an environment. Interestingly, it is shown that ergodic exploration utilizes non-contact motion to gather significant information about shape. The algorithm is extended in three dimensions in simulation and we present two dimensional experimental results using the Rethink Baxter robot.

Mapping Partially Observable Features from Multiple Uncertain Vantage Points

In this paper we present a technique for mapping partially observable features from multiple uncertain vantage points. The problem of concurrent mapping and localization (CML) is stated as follows. Starting from an initial known position, a mobile robot travels through a sequence of positions, obtaining a set of sensor measurements at each position. The goal is to process the sensor data to produce an estimate of the trajectory of the robot while concurrently building a map of the environment. In this paper, we describe a generalized framework for CML that incorporates temporal as well as spatial correlations. The representation is expanded to incorporate past vehicle positions in the state vector. Estimates of the correlations between current and previous vehicle states are explicitly maintained. This enables the consistent initialization of map features using data from multiple time steps. Updates to the map and the vehicle trajectory can also be performed in batches of data acquired from multiple vantage points. The method is illustrated with sonar data from a testing tank and via experiments with a B21 land mobile robot, demonstrating the ability to perform CML with sparse and ambiguous data.

Simultaneous Localization and Map Building in Large-Scale Cyclic Environments Using the Atlas Framework

In this paper we describe Atlas, a hybrid metrical/topological approach to simultaneous localization and mapping (SLAM) that achieves efficient mapping of large-scale environments. The representation is a graph of coordinate frames, with each vertex in the graph representing a local frame and each edge representing the transformation between adjacent frames. In each frame, we build a map that captures the local environment and the current robot pose along with the uncertainties of each. Each map’s uncertainties are modeled with respect to its own frame. Probabilities of entities with respect to arbitrary frames are generated by following a path formed by the edges between adjacent frames, computed using either the Dijkstra shortest path algorithm or breath-first search. Loop closing is achieved via an efficient map-matching algorithm coupled with a cycle verification step. We demonstrate the performance of the technique for post-processing large data sets, including an indoor structured environment (2.2 km path length) with multiple nested loops using laser or ultrasonic ranging sensors.

Robust Mapping and Localization in Indoor Environments Using Sonar Data

In this paper we describe a new technique for the creation of feature-based stochastic maps using standard Polaroid sonar sensors. The fundamental contributions of our proposal are: (1) a perceptual grouping process that permits the robust identification and localization of environmental features, such as straight segments and corners, from the sparse and noisy sonar data; (2) a map joining technique that allows the system to build a sequence of independent limited-size stochastic maps and join them in a globally consistent way; (3) a robust mechanism to determine which features in a stochastic map correspond to the same environment feature, allowing the system to update the stochastic map accordingly, and perform tasks such as revisiting and loop closing. We demonstrate the practicality of this approach by building a geometric map of a medium size, real indoor environment, with several people moving around the robot. Maps built from laser data for the same experiment are provided for comparison.

Constrained Initialization of the Simultaneous Localization and Mapping Algorithm

In this paper we present a novel feature initialization technique for the Simultaneous Localization and Mapping (SLAM) algorithm. The initialization scheme extends previous approaches for identifying new confirmed features and is shown to improve the steady-state performance of the filter by incorporating tentative features into the filter as soon as they are observed. Constraints are then applied between multiple feature estimates when a feature is confirmed. Observations that are subsequently deemed as spurious are removed from the state vector after an appropriate timeout. It is shown that information that would otherwise be lost can therefore be used consistently in the filter. Results of this algorithm applied to data collected using a submersible vehicle are also shown.

Safe Navigation for Indoor Mobile Robots. Part II: Exploration, Self-Localization and Map Building

This paper is the second part of the authors’ contribution on the topic of safe navigation for indoor mobile robots. It presents a new solution to the exploration, self-localization and map building problem taking advantage of the sensor-based navigation framework presented in Part I: A Sensor-Based Navigation Framework. The model of the indoor environment is structured as a hybrid representation, both topological and geometrical, which is incrementally built during the exploration task. The topological aspect of the model captures the connectivity and accessibility of the different places in the environment, and the geometrical model holds up an accurate robot localization and map building method. To overcome the problem of drift inherited to the odometry when the robot navigates in large-scale environments, a new dead-reckoning method is proposed combining laser readings and feedback control inputs. Embedding the selflocalization and map building problem in a sensor-based navigation framework improves both the quality and the robustness of the representation built during the exploration phase and authorizes a further use to achieve safe navigation tasks successfully. Experiments are shown which confirm the interests of the proposed methodology.

Adaptive informative path planning in metric spaces

In contrast to classic geometric motion planning, informative path planning (IPP) seeks a path for a robot to sense the world and gain information. In adaptive IPP, the robot chooses the next sensing location conditioned on all information acquired so far, and the robot’s goal is to minimize the travel cost required for identifying a true hypothesis. Adaptive IPP is NP-hard, because the robot must trade-off information gain and travel cost optimally. In this paper we present Recursive Adaptive Identification (RAId), a new polynomial-time approximation algorithm for adaptive IPP. We prove a polylogarithmic approximation bound when the robot travels in a metric space. Furthermore, our experiments suggest that RAId is practical and provides good approximate solutions for two distinct robot planning tasks. Although RAId is designed primarily for noiseless observations, a simple extension allows it to handle some tasks with noisy observations.

Finding and identifying simple objects underwater with active electrosense

Active electrosense is used by some fish for the sensing of nearby objects by means of the perturbations the objects induce in a self-generated electric field. As with echolocation (sensing via perturbations of an emitted acoustic field) active electrosense is particularly useful in environments where darkness, clutter or turbidity makes vision ineffective. Work on engineered variants of active electrosense is motivated by the need for sensors in underwater systems that function well at short range and where vision-based approaches can be problematic, as well as to aid in understanding the computational principles of biological active electrosense. Prior work in robotic active electrosense has focused on tracking and localization of spherical objects. In this study, we present an algorithm for estimating the size, shape, orientation, and location of ellipsoidal objects, along with experimental results. The algorithm is implemented in a robotic active electrosense system whose basic approach is similar to biological active electrosense systems, including the use of movement as part of sensing. At a range up to ≈20 cm, or about half the length of the robot, the algorithm localizes spheroids that are one-tenth the length of the robot with accuracy of better than 1 cm for position and 5° in orientation. The algorithm estimates object size and length-to-width ratio with an accuracy of around 10%.

Active visual SLAM for robotic area coverage: Theory and experiment

This paper reports on an integrated navigation algorithm for the visual simultaneous localization and mapping (SLAM) robotic area coverage problem. In the robotic area coverage problem, the goal is to explore and map a given target area within a reasonable amount of time. This goal necessitates the use of minimally redundant overlap trajectories for coverage efficiency; however, visual SLAM’s navigation estimate will inevitably drift over time in the absence of loop closures. Therefore, efficient area coverage and good SLAM navigation performance represent competing objectives. To solve this decision-making problem, we introduce perception-driven navigation, an integrated navigation algorithm that automatically balances between exploration and revisitation using a reward framework. This framework accounts for SLAM localization uncertainty, area coverage performance, and the identification of good candidate regions in the environment for visual perception. Results are shown for both a hybrid simulation and real-world demonstration of a visual SLAM system for autonomous underwater ship hull inspection.

Active exploration using a scheme for autonomous allocation of landmarks

In this paper, we focus on the unknown environments without artificial landmarks and features, such as disaster situations and polar regions. An approach to active exploration based on an on-line scheme for autonomous allocation of landmarks is proposed. Specifically, the robot carries along with itself some landmarks which are to be allocated during the exploration according to some heuristic rules. The utility of landmark allocation is analyzed and calculated. Then the active exploration is converted into a problem of multi-objective optimization. The objective function includes three weighted terms: the accuracy of localization and mapping, the coverage rate of the unknown environment and the utility of the allocated landmarks. By solving this optimization problem, control inputs of the robot are computed to guarantee that accurate localization, high-quality mapping and complete exploration can be achieved simultaneously. Moreover, supplementation and redundancy elimination of the allocated landmarks are executed to make a complete and non-redundant coverage for the environment. Finally, some landmarks, together with a device for allocating these landmarks, are developed. Both experiment and simulation results are presented to demonstrate the effectiveness of the proposed approach.

Action selection for single-camera SLAM

A method for evaluating, at video rate, the quality of actions for a single camera while mapping unknown indoor environments is presented. The strategy maximizes mutual information between measurements and states to help the camera avoid making ill-conditioned measurements that are appropriate to lack of depth in monocular vision systems. Our system prompts a user with the appropriate motion commands during 6-DOF visual simultaneous localization and mapping with a handheld camera. Additionally, the system has been ported to a mobile robotic platform, thus closing the control-estimation loop. To show the viability of the approach, simulations and experiments are presented for the unconstrained motion of a handheld camera and for the motion of a mobile robot with nonholonomic constraints. When combined with a path planner, the technique safely drives to a marked goal while, at the same time, producing an optimal estimated map.

Trajectory Optimization using Reinforcement Learning for Map Exploration

Automatically building maps from sensor data is a necessary and fundamental skill for mobile robots; as a result, considerable research attention has focused on the technical challenges inherent in the mapping problem. While statistical inference techniques have led to computationally efficient mapping algorithms, the next major challenge in robotic mapping is to automate the data collection process. In this paper, we address the problem of how a robot should plan to explore an unknown environment and collect data in order to maximize the accuracy of the resulting map. We formulate exploration as a constrained optimization problem and use reinforcement learning to find trajectories that lead to accurate maps. We demonstrate this process in simulation and show that the learned policy not only results in improved map building, but that the learned policy also transfers successfully to a real robot exploring on MIT campus.

Qualitative map learning based on covisibility of objects

Autonomous map construction is one of the most fundamental and significant issues in intelligent mobile robot research. While a variety of map construction methods have been proposed, most require some quantitative measurements of the environment and a mechanism of precise self-localization. This paper proposes a novel map construction method using only qualitative information about "how often two objects are observed simultaneously." This method is based on heuristics--"closely located objects are likely to be seen simultaneously more often than distant objects" and a well-known multivariate data analysis technique-multidimensional scaling. A significant feature of this method is that it requires neither quantitative sensor measurements nor information about the robot's own position. Simulation and experimental results demonstrated that this method is sufficiently practical for capturing a qualitative spatial relationship among identifiable landmark objects rapidly.