Category Archives: Robotics

How “behaviour trees” generalize the subsumption architecture and some other control architecture frameworks

M. Colledanchise and P. Ögren, “How Behavior Trees Modularize Hybrid Control Systems and Generalize Sequential Behavior Compositions, the Subsumption Architecture, and Decision Trees,” in IEEE Transactions on Robotics, vol. 33, no. 2, pp. 372-389, April 2017.DOI: 10.1109/TRO.2016.2633567.

Behavior trees (BTs) are a way of organizing the switching structure of a hybrid dynamical system (HDS), which was originally introduced in the computer game programming community. In this paper, we analyze how the BT representation increases the modularity of an HDS and how key system properties are preserved over compositions of such systems, in terms of combining two BTs into a larger one. We also show how BTs can be seen as a generalization of sequential behavior compositions, the subsumption architecture, and decisions trees. These three tools are powerful but quite different, and the fact that they are unified in a natural way in BTs might be a reason for their popularity in the gaming community. We conclude the paper by giving a set of examples illustrating how the proposed analysis tools can be applied to robot control BTs.

On the current limitations of robotics research concerning the generalization of reported results to different set-ups

Francesco Amigoni, Matteo Luperto, Viola Schiaffonati,Toward generalization of experimental results for autonomous robots, Robotics and Autonomous Systems, Volume 90, April 2017, Pages 4-14, ISSN 0921-8890, DOI: 10.1016/j.robot.2016.08.016.

In this paper we discuss some issues in the experimental evaluation of intelligent autonomous systems, focusing on systems, like autonomous robots, operating in physical environments. We argue that one of the weaknesses of current experimental practices is the low degree of generalization of experimental results, meaning that knowing the performance a robot system obtains in a test setting does not provide much information about the performance the same system could achieve in other settings. We claim that one of the main obstacles to achieve generalization of experimental results in autonomous robotics is the low degree of representativeness of the selected experimental settings. We survey and discuss the degree of representativeness of experimental settings used in a significant sample of current research and we propose some strategies to overcome the emerging limitations.

Robots that pre-compute a number of possible behaviours (in simulation) and then learn their performance with them (propragating that performance measures to similar behaviors through Gaussian Processes Regression) and select the best at each situation (through Bayesian Optimization), thus confronting varying environments and damages to the robot

A. Cully, et al. Robots that can adapt like animals, Nature, 521 (2015), pp. 503–507, DOI: 10.1038/nature14422.

Robots have transformed many industries, most notably manufacturing, and have the power to deliver tremendous benefits to society, such as in search and rescue, disaster response, health care and transportation. They are also invaluable tools for scientific exploration in environments inaccessible to humans, from distant planets to deep oceans. A major obstacle to their widespread adoption in more complex environments outside factories is their fragility. Whereas animals can quickly adapt to injuries, current robots cannot think outside the box to find a compensatory behaviour when they are damaged: they are limited to their pre-specified self-sensing abilities, can diagnose only anticipated failure modes, and require a pre-programmed contingency plan for every type of potential damage, an impracticality for complex robots. A promising approach to reducing robot fragility involves having robots learn appropriate behaviours in response to damage, but current techniques are slow even with small, constrained search spaces. Here we introduce an intelligent trial-and-error algorithm that allows robots to adapt to damage in less than two minutes in large search spaces without requiring self-diagnosis or pre-specified contingency plans. Before the robot is deployed, it uses a novel technique to create a detailed map of the space of high-performing behaviours. This map represents the robotâ €™ s prior knowledge about what behaviours it can perform and their value. When the robot is damaged, it uses this prior knowledge to guide a trial-and-error learning algorithm that conducts intelligent experiments to rapidly discover a behaviour that compensates for the damage. Experiments reveal successful adaptations for a legged robot injured in five different ways, including damaged, broken, and missing legs, and for a robotic arm with joints broken in 14 different ways. This new algorithm will enable more robust, effective, autonomous robots, and may shed light on the principles that animals use to adapt to injury.

Qualitative robot navigation

Sergio Miguel-Tomé, Navigation through unknown and dynamic open spaces using topological notions, Connection Science, DOI: 10.1080/09540091.2016.1277691.

Until now, most algorithms used for navigation have had the purpose of directing system towards one point in space. However, humans communicate tasks by specifying spatial relations among elements or places. In addition, the environments in which humans develop their activities are extremely dynamic. The only option that allows for successful navigation in dynamic and unknown environments is making real-time decisions. Therefore, robots capable of collaborating closely with human beings must be able to make decisions based on the local information registered by the sensors and interpret and express spatial relations. Furthermore, when one person is asked to perform a task in an environment, this task is communicated given a category of goals so the person does not need to be supervised. Thus, two problems appear when one wants to create multifunctional robots: how to navigate in dynamic and unknown environments using spatial relations and how to accomplish this without supervision. In this article, a new architecture to address the two cited problems is presented, called the topological qualitative navigation architecture. In previous works, a qualitative heuristic called the heuristic of topological qualitative semantics (HTQS) has been developed to establish and identify spatial relations. However, that heuristic only allows for establishing one spatial relation with a specific object. In contrast, navigation requires a temporal sequence of goals with different objects. The new architecture attains continuous generation of goals and resolves them using HTQS. Thus, the new architecture achieves autonomous navigation in dynamic or unknown open environments.

Spatio-temporal maps for mobile robots: taking into account time into the map

João Machado Santos, Tomáš Krajník, Tom Duckett, Spatio-temporal exploration strategies for long-term autonomy of mobile robots, Robotics and Autonomous Systems, Volume 88, February 2017, Pages 116-126, ISSN 0921-8890, DOI: 10.1016/j.robot.2016.11.016.

We present a study of spatio-temporal environment representations and exploration strategies for long-term deployment of mobile robots in real-world, dynamic environments. We propose a new concept for life-long mobile robot spatio-temporal exploration that aims at building, updating and maintaining the environment model during the long-term deployment. The addition of the temporal dimension to the explored space makes the exploration task a never-ending data-gathering process, which we address by application of information-theoretic exploration techniques to world representations that model the uncertainty of environment states as probabilistic functions of time. We evaluate the performance of different exploration strategies and temporal models on real-world data gathered over the course of several months. The combination of dynamic environment representations with information-gain exploration principles allows to create and maintain up-to-date models of continuously changing environments, enabling efficient and self-improving long-term operation of mobile robots.

Efficient detection of glass obstacles when using a laser rangefinder

Xun Wang, JianGuo Wang, Detecting glass in Simultaneous Localisation and Mapping, Robotics and Autonomous Systems, Volume 88, February 2017, Pages 97-103, ISSN 0921-8890, DOI: 10.1016/j.robot.2016.11.003.

Simultaneous Localisation and Mapping (SLAM) has become one of key technologies used in advanced robot platform. The current state-of-art indoor SLAM with laser scanning rangefinders can provide accurate realtime localisation and mapping service to mobile robotic platforms such as PR2 robot. In recent years, many modern building designs feature large glass panels as one of the key interior fitting elements, e.g. large glass walls. Due to the transparent nature of glass panels, laser rangefinders are unable to produce accurate readings which causes SLAM functioning incorrectly in these environments. In this paper, we propose a simple and effective solution to identify glass panels based on the specular reflection of laser beams from the glass. Specifically, we use a simple technique to detect the reflected light intensity profile around the normal incident angle to the glass panel. Integrating this glass detection method with an existing SLAM algorithm, our SLAM system is able to detect and localise glass obstacles in realtime. Furthermore, the tests we conducted in two office buildings with a PR2 robot show the proposed method can detect ∼ 95% of all glass panels with no false positive detection. The source code of the modified SLAM with glass detection is released as a open source ROS package along with this paper.

Improving sensory information, diagnosis and fault tolerance by using multiple sensors and sensor fusion, with a good related work section (2.3) on fault tolerance on data fusion

Kaci Bader, Benjamin Lussier, Walter Schön, A fault tolerant architecture for data fusion: A real application of Kalman filters for mobile robot localization, Robotics and Autonomous Systems, Volume 88, February 2017, Pages 11-23, ISSN 0921-8890, DOI: 10.1016/j.robot.2016.11.015.

Multisensor perception has an important role in robotics and autonomous systems, providing inputs for critical functions including obstacle detection and localization. It is starting to appear in critical applications such as drones and ADASs (Advanced Driver Assistance Systems). However, this kind of complex system is difficult to validate comprehensively. In this paper we look at multisensor perception systems in relation to an alternative dependability method, namely fault tolerance. We propose an approach for tolerating faults in multisensor data fusion that is based on the more traditional method of duplication–comparison, and that offers detection and recovery services. We detail an example implementation using Kalman filter data fusion for mobile robot localization. We demonstrate its effectiveness in this case study using real data and fault injection.

A nice summary of motion planning

J. J. M. Lunenburg, S. A. M. Coenen, G. J. L. Naus, M. J. G. van de Molengraft and M. Steinbuch, “Motion Planning for Mobile Robots: A Method for the Selection of a Combination of Motion-Planning Algorithms,” in IEEE Robotics & Automation Magazine, vol. 23, no. 4, pp. 107-117, Dec. 2016. DOI: 10.1109/MRA.2015.2510798.

A motion planner for mobile robots is commonly built out of a number of algorithms that solve the two steps of motion planning: 1) representing the robot and its environment and 2) searching a path through the represented environment. However, the available literature on motion planning lacks a generic methodology to arrive at a combination of representations and search algorithm classes for a practical application. This article presents a method to select appropriate algorithm classes that solve both the steps of motion planning and to select a suitable approach to combine those algorithm classes. The method is verified by comparing its outcome with three different motion planners that have been successfully applied on robots in practice.

Insights into the sparsity of graph-SLAM (i.e., in the smoothing / optimization approach to SLAM) and a good formalization of the problem

K. Khosoussi, S. Huang and G. Dissanayake, “A Sparse Separable SLAM Back-End,” in IEEE Transactions on Robotics, vol. 32, no. 6, pp. 1536-1549, Dec. 2016. DOI: 10.1109/TRO.2016.2609394.

We propose a scalable algorithm to take advantage of the separable structure of simultaneous localization and mapping (SLAM). Separability is an overlooked structure of SLAM that distinguishes it from a generic nonlinear least-squares problem. The standard relative-pose and relative-position measurement models in SLAM are affine with respect to robot and features’ positions. Therefore, given an estimate for robot orientation, the conditionally optimal estimate for the rest of the state variables can be easily computed by solving a sparse linear least-squares problem. We propose an algorithm to exploit this intrinsic property of SLAM by stripping the problem down to its nonlinear core, while maintaining its natural sparsity. Our algorithm can be used in conjunction with any Newton-based solver and is applicable to 2-D/3-D pose-graph and feature-based SLAM. Our results suggest that iteratively solving the nonlinear core of SLAM leads to a fast and reliable convergence as compared to the state-of-the-art sparse back-ends.

An excellent survey of metrical SLAM (and of map representations and other issues related to SLAM) as of 2016

C. Cadena et al., “Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age,” in IEEE Transactions on Robotics, vol. 32, no. 6, pp. 1309-1332, Dec. 2016. DOI: 10.1109/TRO.2016.2624754.

Simultaneous localization and mapping (SLAM) consists in the concurrent construction of a model of the environment (the map), and the estimation of the state of the robot moving within it. The SLAM community has made astonishing progress over the last 30 years, enabling large-scale real-world applications and witnessing a steady transition of this technology to industry. We survey the current state of SLAM and consider future directions. We start by presenting what is now the de-facto standard formulation for SLAM. We then review related work, covering a broad set of topics including robustness and scalability in long-term mapping, metric and semantic representations for mapping, theoretical performance guarantees, active SLAM and exploration, and other new frontiers. This paper simultaneously serves as a position paper and tutorial to those who are users of SLAM. By looking at the published research with a critical eye, we delineate open challenges and new research issues, that still deserve careful scientific investigation. The paper also contains the authors’ take on two questions that often animate discussions during robotics conferences: Do robots need SLAM? and Is SLAM solved?