With the vast demand in marine development, robotic fish show promising potential in underwater exploration for their high-performance propulsion ability. However, fish-inspired robots are yet to utilize the structural flexibility of rhythmic actuation such as bony fish (Osteichthyes). The Body and Caudal Fin (BCF) locomotion in fish optimizes the use of muscle power and body flexibility by synchronizing muscle activation with the undulating-oscillatory tail-flapping, such as Thunniform, while robotic fish are primarily designed as motion trackers rather than as efficient swimmers. In this paper, we propose a power allocation strategy (PAS) that imitates muscle rhythmic actuation, which increases the flapping amplitude by the coupling of the peduncle motion and the tail deformation. Inspired by this peduncle-tail mechanism, we developed a Direct-Drive Fish Robot (DDRFishBot). The DDRFishBot is enhanced by our developed PAS in Tail-Elastic Potential Energy (T-EPE) release by 228%, in propulsion by 45.6% and in efficiency coefficient by 16.3%. This study establishes the performance enhancement principle of exploiting tail flexibility through a simple scotch yoke mechanism, expanding the performance space of fish-inspired tail-flapping swimming robot.

Sampling-based planning algorithms such as RRT have been proved to be efficient in solving path planning problems for robotic systems. Various improvements to the RRT algorithm have been presented to improve the performance of the extension and convergence of the random trees, such as Informed RRT*. However, with the growth of spatial dimensions, the time consumption of randomly sampling the entire state space and incrementally rewiring the random trees raises drastically before a feasible solution is found. In this paper, to enhance the convergence performance of optimal solutions, we present Reconstructed Bi-directional Informed RRT* (RBI-RRT*) path planning algorithm. The algorithm acts as RRT-Connect to rapidly find a feasible solution, which helps compress the sampling space as Informed RRT* does. After the random trees are transformed into RRT* structure by the reconstruction process in RBI-RRT*, the algorithm continues to find the near-optimal path. A series of simulations and real-world robot experiments were conducted to evaluate the algorithm against existing planning algorithms. Compared to Informed RRT* Connect, RBI-RRT* reduced the computation time of achieving a specific cost by 22.1% on average in simulations and 11.2% in the real-world robotic arm experiments. The results show that RBI-RRT* is more efficient in high-dimensional planning problems.

Multiple-object tracking (MOT) is a crucial component in autonomous driving systems. However, inaccurate object detection is always the bottleneck for MOT. Most detectors are not designed to take the temporal information across consecutive frames into consideration. To take advantage of such information, we design a novel data representation, the spatio-temporal (ST) map, which collects a batch of detection results spatio-temporally, and we train a novel network, ST-TrackNet, to assign predicted track IDs to each positive detection across a sequence. With our ST map detection fed into the tracker, the correlation of objects between adjacent frames becomes prominent, which improves the performance of the tracker in the data association step. Moreover, the long-term trajectory in a sequence also helps to refine the detection results. We train and evaluate our network on the KITTI dataset, a CARLA simulation dataset, and a dataset recorded in a factory environment. Our approach generally achieves superior performance over the state-of-the-art. Note to Practitioners—We investigate the MOT problem in this paper. A spatio-temporal pipeline is proposed to provide a solution to this problem. Object detection results produced by off-the-shelf object detectors are used to form the proposed ST maps. In low signal-to-noise ratio (SNR) situations, our proposed framework can achieve more accurate and robust tracking results with more false-positives. Due to the simplicity and modular design of our framework, it can be applied directly after the detection stage to achieve the online tracking task. The proposed method is evaluated on several datasets, and the experimental results demonstrate its effectiveness. Our method can also be used for other autonomous driving applications, such as path planning and trajectory prediction.

Proprioception and variable stiffness are two trending topics in soft robotics research. The former could endow soft robots with the ability to perceive the environment as well as their internal states without the need of dedicated sensors, while the latter could strengthen the otherwise excessive compliance, enabling soft robots for tasks which require a higher force. Both directions have been extensively reported in existing literature, achieving both concurrently was even more challenging. The major limiting factor was the limited stiffness due to the hyper elasticity of conventional soft robots, which increases the difficulties in capturing the continues deformation. In this work, we proposed an alternative approach to tackle these two challenges, a novel “tune-down” approach, combining proprioception with stiffness regulation and implemented over-constrained soft robotic joint designs to further strengthen this spirit. As a result, the soft robotic joint could achieve multi-directional proprioception, as well as variable stiffness tuning, concurrently, using merely an on-board sensor for basic pneumatic control. The concept, design, modeling, actuation/control, and experimental validation were presented in detail, demonstrating the efficacy and potential of the proposed approach.

We propose a deep visuo-tactile model for real-time estimation of the liquid inside a deformable container in a proprioceptive way. We fuse two sensory modalities, i.e., the raw visual inputs from the RGB camera and the tactile cues from our specific tactile sensor without any extra sensor calibrations. The robotic system is well controlled and adjusted based on the estimation model in real time. The main contributions and novelties of our work are listed as follows: 1) Explore a proprioceptive way for liquid volume estimation by developing an end-to-end predictive model with multi-modal convolutional networks, which achieve a high precision with an error of ~ 2 ml in the experimental validation. 2) Propose a multi-task learning architecture which comprehensively considers the losses from both classification and regression tasks, and comparatively evaluate the performance of each variant on the collected data and actual robotic platform. 3) Utilize the proprioceptive robotic system to accurately serve and control the requested volume of liquid, which is continuously flowing into a deformable container in real time. 4) Adaptively adjust the grasping plan to achieve more stable grasping and manipulation according to the real-time liquid volume prediction.

The design of feedback controllers for bipedal robots is challenging due to the hybrid nature of its dynamics and the complexity imposed by high-dimensional bipedal models. In this paper, we present a novel approach for the design of feedback controllers using Reinforcement Learning (RL) and Hybrid Zero Dynamics (HZD). Existing RL approaches for bipedal walking are inefficient as they do not consider the underlying physics, often requires substantial training, and the resulting controller may not be applicable to real robots. HZD is a powerful tool for bipedal control with local stability guarantees of the walking limit cycles. In this paper, we propose a non traditional RL structure that embeds the HZD framework into the policy learning. More specifically, we propose to use RL to find a control policy that maps from the robot’s reduced order states to a set of parameters that define the desired trajectories for the robot’s joints through the virtual constraints. Then, these trajectories are tracked using an adaptive PD controller. The method results in a stable and robust control policy that is able to track variable speed within a continuous interval. Robustness of the policy is evaluated by applying external forces to the torso of the robot. The proposed RL framework is implemented and demonstrated in OpenAI Gym with the MuJoCo physics engine based on the well-known RABBIT robot model.

Fast-growing interests in safe and effective robot-environment interactions stimulated global investigations on soft robotics. The inherent compliance of soft robots ensures promising safety features but drastically reduces force capability, thereby complicating system modeling and control. To tackle these limitations, a soft robotic joint with enhanced strength, servo performance, and impact behavior shaping is proposed in this paper, based on novel three-dimensional-printed soft origami rotary actuators. The complete workflow is presented from the concept of origami design and analytical modeling, joint design, fabrication, control, and validation experiments. The proposed approach facilitates a fully customizable joint design towards the desired force capability and motion range. Validation results from models and experiments using multiple fabricated prototypes proved the excellent performance linearity and superior force capability, with 18.5-N·m maximum torque under 180 kPa, and 300-g self-weight. The behavior shaping capability is achieved by a low-level joint-angle servo and a high-level variable-stiffness regulation; this significantly reduces the impact torque by 53% and ensures powerful and safe interactions. The comprehensive guidelines provide insightful references for soft robotic design for wider robotic applications.

Soft robots are inherently compliant and adaptive, therefore they are promising candidates for interacting with humans. However robotic manipulators utilizing soft actuators are often constrained by a series of actuator performance limitations. In this work we design a novel linear soft robotic actuator with significantly improved performances over the existing products, achieving 300% deformation ratio, quasi-constant output force over a wide motion range, while maintaining passive compliance and adaptability. Moreover, the novel actuator is less prone to friction, and could be fabricated using inject molding and 3D printing, hence having high repeatability at very low cost. An analytical model was developed to characterize the actuator behavior and provide a guideline for actuator design according to performance specifications. A 6 DOF soft manipulator was designed and fabricated utilizing the novel soft actuator. The manipulator arm had a serial kinematic structure with a biomimetic wrist and was driven by 12 soft actuators mounted onto the arm links. With 1.2m workspace radius and 1kg payload, the working air pressure could be as low as 1bar. Preliminary results have shown the validity of the novel soft actuator and manipulator designs, as well as the strong potential of soft robots in human-oriented applications.

Soft fluidic actuators consisting of elastomeric matrices with embedded flexible materials are of particular interest to the robotics community because they are affordable and can be easily customized to a given application. However, the significant potential of such actuators is currently limited as their design has typically been based on intuition. In this paper, the principle of operation of these actuators is comprehensively analyzed and described through experimentally validated quasi-static analytical and finite-element method models for bending in free space and force generation when in contact with an object. This study provides a set of systematic design rules to help the robotics community create soft actuators by understanding how these vary their outputs as a function of input pressure for a number of geometrical parameters. Additionally, the proposed analytical model is implemented in a controller demonstrating its ability to convert pressure information to bending angle in real time. Such an understanding of soft multimaterial actuators will allow future design concepts to be rapidly iterated and their performance predicted, thus enabling new and innovative applications that produce more complex motions to be explored.

This paper presents preliminary results for the design, development and evaluation of a hand rehabilitation glove fabricated using soft robotic technology. Soft actuators comprised of elastomeric materials with integrated channels that function as pneumatic networks (PneuNets), are designed and geometrically analyzed to produce bending motions that can safely conform with the human finger motion. Bending curvature and force response of these actuators are investigated using geometrical analysis and a finite element model (FEM) prior to fabrication. The fabrication procedure of the chosen actuator is described followed by a series of experiments that mechanically characterize the actuators. The experimental data is compared to results obtained from FEM simulations showing good agreement. Finally, an open-palm glove design and the integration of the actuators to it are described, followed by a qualitative evaluation study.