Real-world embodied AI through a morphologically adaptive quadruped robot

Multimodal Soft Robotic Actuation and Locomotion

Diverse and adaptable modes of complex motion observed at different scales in living creatures are challenging to reproduce in robotic systems. Achieving dexterous movement in conventional robots can be difficult due to the many limitations of applying rigid materials. Robots based on soft materials are inherently deformable, compliant, adaptable, and adjustable, making soft robotics conducive to creating machines with complicated actuation and motion gaits. This review examines the mechanisms and modalities of actuation deformation in materials that respond to various stimuli. Then, strategies based on composite materials are considered to build toward actuators that combine multiple actuation modes for sophisticated movements. Examples across literature illustrate the development of soft actuators as free-moving, entirely soft-bodied robots with multiple locomotion gaits via careful manipulation of external stimuli. The review further highlights how the application of soft functional materials into robots with rigid components further enhances their locomotive abilities. Finally, taking advantage of the shape-morphing properties of soft materials, reconfigurable soft robots have shown the capacity for adaptive gaits that enable transition across environments with different locomotive modes for optimal efficiency. Overall, soft materials enable varied multimodal motion in actuators and robots, positioning soft robotics to make real-world applications for intricate and challenging tasks.

Fully 3D-printed tortoise-like soft mobile robot with muti-scenario adaptability

Soft robotic systems are well suited to unstructured, dynamic tasks and environments, owing to their ability to adapt and conform without damaging themselves or their surroundings. These abilities are crucial in areas such as human-robot interaction, simplification of control system and weight reduction. At present, the existing soft mobile robots still have the disadvantages of single motion mode and application scenario, difficult manufacturing and low energy conversion efficiency. Based on the current shortcomings of soft robots, this paper designs and proposes a fully 3D-printed tortoise-like soft mobile robot with muti-scenarios adaptability. The robot uses a Bionic Tortoise Leg Actuator structure that enables simultaneous bending of the actuator in both directions, simplifying robot control and increasing the maximum bending angle achievable. In addition, a reconfiguration design solution has been proposed to enable the robot to implement two bionic modes for land and sea turtles, adapting to move on hard and soft surfaces and in water, enabling it to move in amphibious and complex environments. The performance of the pneumatic soft actuator is also improved by an improved Digital Light Processing method that enhances the maximum strain of the 3D printed soft material. The prototype was tested to give maximum movement speeds for different gaits and environments, demonstrating that the fully 3D printed tortoise-like soft-mobile robot designed in this paper is highly adaptable to multiple scenarios. The robot studied in this paper has a wide range of applications, with potential applications including navigation in a variety of domain environments, inspection of large underground oil and gas pipelines, and navigation in high temperature, high humidity and strong magnetic field environments or in military alert conditions.

Embedded shape morphing for morphologically adaptive robots

Shape-morphing robots can change their morphology to fulfill different tasks in varying environments, but existing shape-morphing capability is not embedded in a robot's body, requiring bulky supporting equipment. Here, we report an embedded shape-morphing scheme with the shape actuation, sensing, and locking, all embedded in a robot's body. We showcase this embedded scheme using three morphing robotic systems: 1) self-sensing shape-morphing grippers that can adapt to objects for adaptive grasping; 2) a quadrupedal robot that can morph its body shape for different terrestrial locomotion modes (walk, crawl, or horizontal climb); 3) an untethered robot that can morph its limbs' shape for amphibious locomotion. We also create a library of embedded morphing modules to demonstrate the versatile programmable shapes (e.g., torsion, 3D bending, surface morphing, etc.). Our embedded morphing scheme offers a promising avenue for robots to reconfigure their morphology in an embedded manner that can adapt to different environments on demand.

Central pattern generators evolved for real-time adaptation to rhythmic stimuli

For a robot to be both autonomous and collaborative requires the ability to adapt its movement to a variety of external stimuli, whether these come from humans or other robots. Typically, legged robots have oscillation periods explicitly defined as a control parameter, limiting the adaptability of walking gaits. Here we demonstrate a virtual quadruped robot employing a bio-inspired central pattern generator (CPG) that can spontaneously synchronize its movement to a range of rhythmic stimuli. Multi-objective evolutionary algorithms were used to optimize the variation of movement speed and direction as a function of the brain stem drive and the centre of mass control respectively. This was followed by optimization of an additional layer of neurons that filters fluctuating inputs. As a result, a range of CPGs were able to adjust their gait pattern and/or frequency to match the input period. We show how this can be used to facilitate coordinated movement despite differences in morphology, as well as to learn new movement patterns.

Evaluating the Forest Ecosystem through a Semi-Autonomous Quadruped Robot and a Hexacopter UAV

Accurate and timely monitoring is imperative to the resilience of forests for economic growth and climate regulation. In the UK, forest management depends on citizen science to perform tedious and time-consuming data collection tasks. In this study, an unmanned aerial vehicle (UAV) equipped with a light sensor and positioning capabilities is deployed to perform aerial surveying and to observe a series of forest health indicators (FHIs) which are inaccessible from the ground. However, many FHIs such as burrows and deadwood can only be observed from under the tree canopy. Hence, we take the initiative of employing a quadruped robot with an integrated camera as well as an external sensing platform (ESP) equipped with light and infrared cameras, computing, communication and power modules to observe these FHIs from the ground. The forest-monitoring time can be extended by reducing computation and conserving energy. Therefore, we analysed different versions of the YOLO object-detection algorithm in terms of accuracy, deployment and usability by the EXP to accomplish an extensive low-latency detection. In addition, we constructed a series of new datasets to train the YOLOv5x and YOLOv5s for recognising FHIs. Our results reveal that YOLOv5s is lightweight and easy to train for FHI detection while performing close to real-time, cost-effective and autonomous forest monitoring.

PSTO: Learning Energy-Efficient Locomotion for Quadruped Robots

Energy efficiency is critical for the locomotion of quadruped robots. However, energy efficiency values found in simulations do not transfer adequately to the real world. To address this issue, we present a novel method, named Policy Search Transfer Optimization (PSTO), which combines deep reinforcement learning and optimization to create energy-efficient locomotion for quadruped robots in the real world. The deep reinforcement learning and policy search process are performed by the TD3 algorithm and the policy is transferred to the open-loop control trajectory further optimized by numerical methods, and conducted on the robot in the real world. In order to ensure the high uniformity of the simulation results and the behavior of the hardware platform, we introduce and validate the accurate model in simulation including consistent size and fine-tuning parameters. We then validate those results with real-world experiments on the quadruped robot Ant by executing dynamic walking gaits with different leg lengths and numbers of amplifications. We analyze the results and show that our methods can outperform the control method provided by the state-of-the-art policy search algorithm TD3 and sinusoid function on both energy efficiency and speed.

A soft thumb-sized vision-based sensor with accurate all-round force perception

Vision-based haptic sensors have emerged as a promising approach to robotic touch due to affordable high-resolution cameras and successful computer vision techniques; however, their physical design and the information they provide do not yet meet the requirements of real applications. We present a robust, soft, low-cost, vision-based, thumb-sized three-dimensional haptic sensor named Insight, which continually provides a directional force-distribution map over its entire conical sensing surface. Constructed around an internal monocular camera, the sensor has only a single layer of elastomer over-moulded on a stiff frame to guarantee sensitivity, robustness and soft contact. Furthermore, Insight uniquely combines photometric stereo and structured light using a collimator to detect the three-dimensional deformation of its easily replaceable flexible outer shell. The force information is inferred by a deep neural network that maps images to the spatial distribution of three-dimensional contact force (normal and shear). Insight has an overall spatial resolution of 0.4 mm, a force magnitude accuracy of around 0.03 N and a force direction accuracy of around five degrees over a range of 0.03–2 N for numerous distinct contacts with varying contact area. The presented hardware and software design concepts can be transferred to a wide variety of robot parts.

Organic neuromorphic electronics for sensorimotor integration and learning in robotics

In living organisms, sensory and motor processes are distributed, locally merged, and capable of forming dynamic sensorimotor associations. We introduce a simple and efficient organic neuromorphic circuit for local sensorimotor merging and processing on a robot that is placed in a maze. While the robot is exposed to external environmental stimuli, visuomotor associations are formed on the adaptable neuromorphic circuit. With this on-chip sensorimotor integration, the robot learns to follow a path to the exit of a maze, while being guided by visually indicated paths. The ease of processability of organic neuromorphic electronics and their unconventional form factors, in combination with education-purpose robotics, showcase a promising approach of an affordable, versatile, and readily accessible platform for exploring, designing, and evaluating behavioral intelligence through decentralized sensorimotor integration.