机器人行为选择机制综述

详细综述了现有的机器人行为选择方法及国内外研究现状,并讨论了行为选择机制研究发展的趋势, 特别对受生物启发的机器人行为选择机制作了重点介绍．文章最后分析了机器人行为选择研究存在的问题并对以后 的研究方向作了展望．     

Building brains for bodies

We describe a project to capitalize on newly available levels of computational resources in order to understand human cognition. We are building an integrated physical system including vision, sound input and output, and dextrous manipulation, all controlled by a continuously operating large scale parallel MIMD computer. The resulting system will learn to think by building on its bodily experiences to accomplish progressively more abstract tasks. Past experience suggests that in attempting to build such an integrated system we will have to fundamentally change the way artificial intelligence, cognitive science, linguistics, and philosophy think about the organization of intelligence. We expect to be able to better reconcile the theories that will be developed with current work in neuroscience.     

Soft Robotic-Adapted Multimodal Sensors Derived from Entirely Intrinsic Self-Healing and Stretchable Cross-Linked Networks

Flexible sensing technologies that play a pivotal role in endowing robots with detection capabilities and monitoring their motions are impulsively desired for intelligent robotics systems. However, integrating and constructing reliable and sustainable flexible sensors with multifunctionality for robots remains an everlasting challenge. Herein, an entirely intrinsic self-healing, stretchable, and attachable multimodal sensor is developed that can be conformally integrated with soft robots to identify diverse signals. The dynamic bonds cross-linked networks including the insulating polymer and conductive hydrogel with good comprehensive performances are designed to fabricate the sensor with prolonged lifespan and improved reliability. Benefiting from the self-adhesiveness of the hydrogel, strong interfacial bonding can be formed on various surfaces, which promotes the conformable integration of the sensor with robots. Due to the ionic transportation mechanism, the sensor can detect strain and temperature based on piezoresistive and thermoresistive effect, respectively. Moreover, the sensor can work in triboelectric mode to achieve self-powered sensing. Various information can be identified from the electrical signals generated by the sensor, including hand gestures, soft robot crawling motions, a message of code, the temperature of objects, and the type of materials, holding great promise in the fields of environmental detection, wearable devices, human-machine interfacing, and robotics.     

Recent Development of Jumping Motions Based on Soft Actuators

Drawing inspiration from the jumping motions of living creatures in nature, jumping robots have emerged as a promising research field over the past few decades due to great application potential in interstellar exploration, military reconnaissance, and life rescue missions. Early reviews mainly focused on jumping robots made of lightweight and rigid materials with mechanical components, concentrating on jumping control and stability. Herein, attention is paid to the jumping mechanisms of soft actuators assembled from various soft smarting materials and powered by different stimulus sources. The challenges and prospects of soft jumping actuators are also discussed. It is hoped that this review will contribute to the further development of soft jumping actuators and broaden their practical applications.     

Highly Conductive MXene/PEDOT:PSS-Integrated Poly(N-Isopropylacrylamide) Hydrogels for Bioinspired Somatosensory Soft Actuators

Sophisticated sensing and actuation capabilities of many living organisms in nature have inspired scientists to develop biomimetic somatosensory soft robots. Herein, the design and fabrication of homogeneous and highly conductive hydrogels for bioinspired somatosensory soft actuators are reported. The conductive hydrogels are synthesized by in situ copolymerization of conductive surface-functionalized MXene/Poly(3,4-ethylenedioxythiophene)/poly(styrenesulfonate) ink with thermoresponsive poly(N-isopropylacrylamide) hydrogels. The resulting hydrogels are found to exhibit high conductivity (11.76 S m⁻¹), strain sensitivity (GF of 9.93), broad working strain range (≈560% strain), and high stability after over 300 loading–unloading cycles at 100% strain. Importantly, shape-programmable somatosensory hydrogel actuators with rapid response, light-driven remote control, and self-sensing capability are developed by chemically integrating the conductive hydrogels with a structurally colored polymer. As the proof-of-concept illustration, structurally colored hydrogel actuators are applied for devising light-driven programmable shape-morphing of an artificial octopus, an artificial fish, and a soft gripper that can simultaneously monitor their own motions via real-time resistance variation. This work is expected to offer new insights into the design of advanced somatosensory materials with self-sensing and actuation capabilities, and pave an avenue for the development of soft-matter-based self-regulatory intelligence via built-in feedback control that is of paramount significance for intelligent soft robotics and automated machines.     

Development,integration, and field evaluation of an autonomous citrus-harvesting robot

Citrus harvesting is a labor-intensive and time-intensive task. As the global population continues to age, labor costs are increasing dramatically. Therefore, the citrus-harvesting robot has attracted considerable attention from the business and academic communities. However, robotic harvesting in unstructured and natural citrus orchards remains a challenge. This study aims to address some challenges faced in commercializing citrus-harvesting robots. We present a fully integrated, autonomous, and innovative solution for citrus-harvesting robots to overcome the harvesting difficulties derived from the natural growth characteristics of citrus. This solution uses a fused simultaneous localization and mapping algorithm based on multiple sensors to perform high-precision localization and navigation for the robot in the field orchard. Besides, a novel visual method for estimating fruit poses is proposed to cope with the randomization of citrus growth orientations. Further, a new end-effector is designed to improve the success and conformity rate of citrus stem cutting. Finally, a fully autonomous harvesting robot system has been developed and integrated. Field evaluations showed that the robot could harvest citrus continuously with an overall success rate of 87.2% and an average picking time of 10.9 s/fruit. These efforts provide a solid foundation for the future commercialization of citrus-harvesting robots.     

Two-way D algorithm for path planning and replanning

Inspired by the Witkowski’s algorithm, we introduce a novel path planning and replanning algorithm — the two-way D^∗ (TWD^∗) algorithm — based on a two-dimensional occupancy grid map of the environment. Unlike the Witkowski’s algorithm, which finds optimal paths only in binary occupancy grid maps, the TWD^∗ algorithm can find optimal paths in weighted occupancy grid maps. The optimal path found by the TWD^∗ algorithm is the shortest possible path for a given occupancy grid map of the environment. This path is more natural than the path found by the standard D^∗ algorithm as it consists of straight line segments with continuous headings. The TWD^∗ algorithm is tested and compared to the D^∗ and Witkowski’s algorithms by extensive simulations and experimentally on a Pioneer 3DX mobile robot equipped with a laser range finder.     

Buoyancy engine developed for underwater gliders

A buoyancy engine with a swashplate-type axial piston pump was developed. Its oil extrusion and drawing properties under high hydraulic pressure were evaluated. This buoyancy engine is now installed in an underwater glider that will achieve long-term monitoring of ocean environments up to 2100 m depth in a designated area with lower operational costs. This bidirectionally functioning pump can control the amount of oil in extrusion and draw operations. When drawing oil under high pressure, the hydraulic pump and the electric motor, respectively, act as a hydraulic motor and an electric generator. The generated electric power is absorbed by a damping resistor. The oil-drawing and extrusion properties were measured using a large hyperbaric chamber that is able to produce an almost identical environment to that of actual operations. Results confirmed stable oil extrusion operations up to 21 MPa. Regarding oil-drawing properties, although it was measured only up to 10 MPa in the hyperbaric chamber, it can be inferred that the system can draw the oil and can control the buoyancy precisely up to 21 MPa by replacing the two-way ball valve with an electromagnetic latching solenoid valve.     

Planning and execution through variable resolution planning

Generating sequences of actions–plans–for robots using Automated Planning in stochastic and dynamic environments has been shown to be a difficult task with high computational complexity. These plans are composed of actions whose execution might fail due to different reasons. In many cases, if the execution of an action fails, it prevents the execution of some (or all) of the remainder actions in the plan. Therefore, in most real-world scenarios computing a complete and sound (valid) plan at each (re-)planning step is not worth the computational resources and time required to generate the plan. This is specially true given the high probability of plan execution failure. Besides, in many real-world environments, plans must be generated fast, both at the start of the execution and after every execution failure. In this paper, we present Variable Resolution Planning which uses Automated Planning to quickly compute a reasonable (not necessarily sound) plan. Our approach computes an abstract representation–removing some information from the planning task–which is used once a search depth of $k$ steps has been reached. Thus, our approach generates a plan where the first $k$ actions are applicable if the domain is stationary and deterministic, while the rest of the plan might not be necessarily applicable. The advantages of this approach are that it: is faster than regular full-fledged planning (both in the probabilistic or deterministic settings); does not spend much time on the far future actions that probably will not be executed, since in most cases it will need to replan before executing the end of the plan; and takes into account some information of the far future, as an improvement over pure reactive systems. We present experimental results on different robotics domains that simulate tasks on stochastic environments.     

Model-free learning on robot kinematic chains using a nested multi-agent topology

This paper proposes a model-free learning scheme for the developmental acquisition of robot kinematic control and dexterous manipulation skills. The approach is based on a nested-hierarchical multi-agent architecture that intuitively encapsulates the topology of robot kinematic chains, where the activity of each independent degree-of-freedom (DOF) is finally mapped onto a distinct agent. Each one of those agents progressively evolves a local kinematic control strategy in a game-theoretic sense, that is, based on a partial (local) view of the whole system topology, which is incrementally updated through a recursive communication process according to the nested-hierarchical topology. Learning is thus approached not through demonstration and training but through an autonomous self-exploration process. A fuzzy reinforcement learning scheme is employed within each agent to enable efficient exploration in a continuous state–action domain. This paper constitutes in fact a proof of concept, demonstrating that global dexterous manipulation skills can indeed evolve through such a distributed iterative learning of local agent sensorimotor mappings. The main motivation behind the development of such an incremental multi-agent topology is to enhance system modularity, to facilitate extensibility to more complex problem domains and to improve robustness with respect to structural variations including unpredictable internal failures. These attributes of the proposed system are assessed in this paper through numerical experiments in different robot manipulation task scenarios, involving both single and multi-robot kinematic chains. The generalisation capacity of the learning scheme is experimentally assessed and robustness properties of the multi-agent system are also evaluated with respect to unpredictable variations in the kinematic topology. Furthermore, these numerical experiments demonstrate the scalability properties of the proposed nested-hierarchical architecture, where new agents can be recursively added in the hierarchy to encapsulate individual active DOFs. The results presented in this paper demonstrate the feasibility of such a distributed multi-agent control framework, showing that the solutions which emerge are plausible and near-optimal. Numerical efficiency and computational cost issues are also discussed.