Context:
Robotics software architecture-based self-adaptive systems (RSASSs) are robotics systems made robust to runtime uncertainty by adapting their software architectures. The research landscape of RSASS approaches is multidisciplinary and fragmented, with many aspects still unexplored or ineffectively shared among communities involved.

Objective:
We aim at identifying, classifying, and analyzing the state of the art of existing approaches for RSASSs from the following perspectives: (i) the key characteristics of approaches and (ii) the evaluation strategies applied by researchers.

Method:
We apply the systematic mapping research method. We selected
primary studies via automatic, manual, and snowballing-based search and selection procedures. We rigorously defined and applied a classification framework composed of 32 parameters and synthesize the obtained data to produce a comprehensive overview of the state of the art.

Results:
This work contributes (i) a rigorously defined classification framework for studies on RSASSs, (ii) a systematic map of the research efforts on RSASSs, (iii) a discussion of emerging findings and implications for future research, and (iv) a publicly available replication package.

Conclusion:
This study provides a solid evidence-based overview of the state of the art in RSASS approaches. Its results can benefit RSASS researchers at different levels of seniority and involvement in RSASS research.@en

Task and Motion Planning (TAMP) has made strides in complex manipulation tasks, yet the execution robustness of the planned solutions remains overlooked. In this work, we propose a method for reactive TAMP to cope with runtime uncertainties and disturbances. We combine an Active Inference planner (AIP) for adaptive high-level action selection and a novel Multi-Modal Model Predictive Path Integral controller (M3P2I) for low-level control. This results in a scheme that simultaneously adapts both high-level actions and low-level motions. The AIP generates alternative symbolic plans, each linked to a cost function for M3P2I. The latter employs a physics simulator for diverse trajectory rollouts, deriving optimal control by weighing the different samples according to their cost. This idea enables blending different robot skills for fluid and reactive plan execution, accommodating plan adjustments at both the high and low levels to cope, for instance, with dynamic obstacles or disturbances that invalidate the current plan. We have tested our approach in simulations and real-world scenarios.

@en

Self-adaptation can be used in robotics to increase system robust- ness and reliability. This work describes the Metacontrol method for self-adaptation in robotics. Particularly, it details how the MROS (Metacontrol for ROS Systems) framework implements and pack- ages Metacontrol, and it demonstrate how MROS can be applied in a navigation scenario where a mobile robot navigates in a factory floor. Video: https://www.youtube.com/watchvISe9aMskJuE

@en

In this article, we propose a hybrid combination of active inference and behavior trees (BTs) for reactive action planning and execution in dynamic environments, showing how robotic tasks can be formulated as a free-energy minimization problem. The proposed approach allows handling partially observable initial states and improves the robustness of classical BTs against unexpected contingencies while at the same time reducing the number of nodes in a tree. In this work, we specify the nominal behavior offline, through BTs. However, in contrast to previous approaches, we introduce a new type of leaf node to specify the desired state to be achieved rather than an action to execute. The decision of which action to execute to reach the desired state is performed online through active inference. This results in continual online planning and hierarchical deliberation. By doing so, an agent can follow a predefined offline plan while still keeping the ability to locally adapt and take autonomous decisions at runtime, respecting safety constraints. We provide proof of convergence and robustness analysis, and we validate our method in two different mobile manipulators performing similar tasks, both in a simulated and real retail environment. The results showed improved runtime adaptability with a fraction of the hand-coded nodes compared to classical BTs.

@en

Once deployed in the real world, autonomous underwater vehicles (AUVs) are out of reach for human supervision yet need to take decisions to adapt to unstable and unpredictable environments. To facilitate research on self-adaptive AUVs, this paper presents SUAVE, an exemplar for two-layered system-level adaptation of AUVs, which clearly separates the application and self-adaptation concerns. The exemplar focuses on a mission for underwater pipeline inspection by a single AUV, implemented as a ROS 2-based system. This mission must be completed while simultaneously accounting for uncertainties such as thruster failures and unfavorable environmental conditions. The paper discusses how SUAVE can be used with different self-adaptation frameworks, illustrated by an experiment using the Metacontrol framework to compare AUV behavior with and without self-adaptation. The experiment shows that the use of Metacontrol to adapt the AUV during its mission improves its performance when measured by the overall time taken to complete the mission or the length of the inspected pipeline.

@en

Nowadays smart applications appear in domains spanning from commodity household applications to advanced underwater robotics. These smart applications require adaptation to dynamic environments, changing requirements and internal system errors Metacontrol takes a systems of systems view on autonomous control systems and self-adaptation, by means of an additional layer of control that manipulates and combines the regular controllers. This paper develops a formal model of a Metacontrol architecture. We formalise this Metacontrol architecture in the context of an autonomous house heating application, enabling different controllers to be dynamically combined in order to meet user requirements to a better extent than the individual controllers in isolation. The formal model is developed in the Maude rewriting system, where we show results comparing different scenarios.

@en

This work presents a fault-tolerant control scheme for sensory faults in robotic manipulators based on active inference. In the majority of existing schemes a binary decision of whether a sensor is healthy (functional) or faulty is made based on measured data. The decision boundary is called a threshold and it is usually deterministic. Following a faulty decision, fault recovery is obtained by excluding the malfunctioning sensor. We propose a stochastic fault-tolerant scheme based on active inference and precision learning which does not require a priori threshold definitions to trigger fault recovery. Instead, the sensor precision, which represents its health status, is learned online in a model-free way allowing the system to gradually, and not abruptly exclude a failing unit. Experiments on a robotic manipulator show promising results and directions for future work are discussed.

@en

Known attempts to build autonomous robots rely on complex control architectures, often implemented with the Robot Operating System platform (ROS). The implementation of adaptable architectures is very often ad hoc, quickly gets cumbersome and expensive. Reusable solutions that support complex, runtime reasoning for robot adaptation have been seen in the adoption of ontologies. While the usage of ontologies significantly increases system reuse and maintainability, it requires additional effort from the application developers to translate requirements into formal rules that can be used by an ontological reasoner. In this paper, we present a design tool that facilitates the specification of reconfigurable robot skills. Based on the specified skills, we generate corresponding runtime models for self-adaptation that can be directly deployed to a running robot that uses a reasoning approach based on ontologies. We demonstrate the applicability of the tool in a real robot performing a patrolling mission at a university campus.

@en

Autonomous systems are expected to maintain a dependable operation without human intervention. They are intended to fulfill the mission for which they were deployed, properly handling the disturbances that may affect them. Underwater robots, such as the UX-1 mine explorer developed in the UNEXMIN project, are paradigmatic examples of this need. Underwater robots are affected by both external and internal disturbances that hamper their capability for autonomous operation. Long-term autonomy requires not only the capability of perceiving and properly acting in open environments but also a sufficient degree of robustness and resilience so as to maintain and recover the operational functionality of the system when disturbed by unexpected events. In this article, we analyze the operational conditions for autonomous underwater robots with a special emphasis on the UX-1 miner explorer. We then describe a knowledge-based self-awareness and metacontrol subsystem that enables the autonomous reconfiguration of the robot subsystems to keep mission-oriented capability. This resilience augmenting solution is based on the deep modeling of the functional architecture of the autonomous robot in combination with ontological reasoning to allow self-diagnosis and reconfiguration during operation. This mechanism can transparently use robot functional redundancy to ensure mission satisfaction, even in the presence of faults.

@en

This work presents a novel fault-tolerant control scheme based on active inference. Specifically, a new formulation of active inference which, unlike previous solutions, provides unbiased state estimation and simplifies the definition of probabilistically robust thresholds for fault-tolerant control of robotic systems using the free-energy. The proposed solution makes use of the sensory prediction errors in the free-energy for the generation of residuals and thresholds for fault detection and isolation of sensory faults, and it does not require additional controllers for fault recovery. Results validating the benefits in a simulated 2-DOF manipulator are presented, and future directions to improve the current fault recovery approach are discussed.@en

More adaptive controllers for robot manipulators are needed, which can deal with large model uncertainties. This letter presents a novel active inference controller (AIC) as an adaptive control scheme for industrial robots. This scheme is easily scalable to high degrees-of-freedom, and it maintains high performance even in the presence of large unmodeled dynamics. The proposed method is based on active inference, a promising neuroscientific theory of the brain, which describes a biologically plausible algorithm for perception and action. In this work, we formulate active inference from a control perspective, deriving a model-free control law which is less sensitive to unmodeled dynamics. The performance and the adaptive properties of the algorithm are compared to a state-of-the-art model reference adaptive controller (MRAC) in an experimental setup with a real 7-DOF robot arm. The results showed that the AIC outperformed the MRAC in terms of adaptability, providing a more general control law. This confirmed the relevance of active inference for robot control.@en

We present a fault tolerant control scheme for robot manipulators based on active inference. The proposed solution makes use of the sensory prediction errors in the free-energy to simplify the residuals and thresholds generation for fault detection and isolation and does not require additional controllers for fault recovery. Results validating the benefits in a simulated 2DOF manipulator are presented and the limitations of the current approach are highlighted.

@en

Autonomous underwater robots, such as the UX-1 developed in the UNEXMIN project, need to maintain reliable autonomous operation in hazardous and unknown environments. Because of the lack of any kind of real-time communications with a human operated command and control station, the control architecture needs to be enhanced with mission-level self-diagnosis and self-adaptation properties an additional provided by some kind of supervisory or “metacontrol” component to ensure its reliability. In this paper, we propose an ontological implementation of such component based on Web Ontology Language (OWL) and the Semantic Web Rule Language (SWRL). The solution is based on an ontology of the functional architecture of autonomous robots, which allows inferring the effects of the performance of its constituents components in the functions required during the robot mission, and generate the reconfigurations needed to maintain operation reliably. The concept solution has been validated using a hypothetical set of scenarios implemented in an OWL ontology and an OWLAPI-based reasoner, which we aim at validating by integrating the metacontrol reasoning with a realistic simulation of the underwater robot.

@en

This comprehensive resource provides systems engineers and practitioners with the analytic, design and modeling tools of the Model Based Systems Engineering (MBSE) methodology of Integrated Systems Engineering (ISE) and Pipelines of Processes in Object Oriented Architectures (PPOOA) methodology. This methodology integrates model based systems and software engineering approaches for the development of complex products, including aerospace, robotics and energy.@en

This article describes Team Delft's robot winning the Amazon Robotics Challenge 2016. The competition involves automating pick and place operations in semi-structured environments, specifically the shelves in an Amazon warehouse.
Team Delft's entry demonstrated that current robot technology can already address most of the challenges in product handling: object recognition, grasping, motion, or task planning; under broad yet bounded conditions. The system combines an industrial robot arm, 3D cameras and a custom gripper. The robot's software is based on the Robot Operating System to implement solutions based on deep learning and other state-of-the-art artificial intelligence techniques, and to integrate them with off-the-shelf components.
From the experience developing the robotic system it was concluded that: 1) the specific task conditions should guide the selection of the solution for each capability required, 2) understanding the characteristics of the individual solutions and the assumptions they embed is critical to integrate a performing system from them, and 3) this characterization can be based on `levels of robot automation'. This paper proposes automation levels based on the usage of information at
design or runtime to drive the robot's behaviour, and uses them to discuss Team Delft's design solution and the lessons learned from this robot development experience.
@en

Robot control software endows robots with advanced capabilities for autonomous operation, such as navigation, object recognition or manipulation, in unstructured and dynamic environments. However, there is a steady need for more robust operation, where robots should perform complex tasks by reliably exploiting these novel capabilities. Mission-level resilience is required in the presence of component faults through failure recovery.To address this challenge, a novel self-adaptation framework based on functional knowledge for augmented autonomy is presented. A metacontroller is integrated on top of the robot control system,and it uses an explicit run-time model of the robot’s controller and its mission to adapt to operational changes. The model is grounded on a functional ontology that relates the robot’s mission with the robot’s architecture, and it is generated during the robot’s development from its engineering models. Advantages are discussed from both theoretical and practical viewpoints. An application example in a real autonomous mobile robot is provided. In this example, the generic metacontroller uses the robot’s functional model to adapt the control architecture to recover from a sensor failure.@en

This paper describes Team Delft’s robot, which won the Amazon Picking Challenge 2016, including both the Picking and the Stowing competitions. The goal of the challenge is to automate pick and place operations in unstructured environments, specifically the shelves in an Amazon warehouse. Team Delft’s robot is based on an industrial robot arm, 3D cameras and a customized gripper. The robot’s software uses ROS to integrate off-the-shelf components and modules developed specifically for the competition, implementing Deep Learning and other AI techniques for object recognition and pose estimation, grasp planning and motion planning. This paper describes the main components in the system, and discusses its performance and results at the Amazon Picking Challenge 2016 finals.

@en

Cognitive systems are starting to be deployed as appliances across the technological landscape of modern societies. The increasing availability of high performance computing platforms has opened an opportunity for statistics-based cognitive systems that perform quite as humans in certain tasks that resisted the symbolic methods of classic artificial intelligence. Cognitive artefacts appear every day in the media, raising a wave of mild fear concerning artificial intelligence and its impact on society. These systems, performance notwithstanding, are quite brittle and their reduced dependability limips their potential for massive deployment in mission-critical applications -e.g. in autonomous driving or medical diagnosis. In this paper we explore the actual possibility of building cognitive systems using engineering-grade methods that can assure the satisfaction of strict requirements for their operation. The final conclusion will be that, besides the potential improvement provided by a rigorous engineering process, we are still in need of a solid theory -possibly the main outcome of cognitive science- that could sustain such endeavour. In this sense, we propose the use of formal ontologies as backbones of cognitive systems engineering processes and workflows.

@en

Nowadays we find ourselves in what is called the fourth industrial revolution: Industry 4.0. This revolution is being fostered in many countries to get a more competitive industry. Industry 4.0 target is to make more efficient and flexible plants, reduce times and costs of process and products lifecycle. Under this framework, models appear as a core component in every new development. Model-Based Systems Engineering is a methodology that allows for traceability and guarantees model consistency covering the entire lifecycle of the system. The objective of this work is to develop a holistic model of a process plant. Such model will be available during the entire lifecycle of the system (process + product) communicating in every stage with the specific (existing) tools used to develop it. In this paper, we present the development of the SysML model of a process plant (the production of ethylbenzene from benzene and ethylene), the architecture and the methodology to transform the central model to application-specific ones. We also explain how to execute these specific models from the core model keeping consistency between models and data.@en