skip to main content


Title: Learning to Locomote with Artificial Neural-Network and CPG-based Control in a Soft Snake Robot
In this paper, we present a new locomotion control method for soft robot snakes. Inspired by biological snakes, our control architecture is composed of two key modules: A reinforcement learning (RL) module for achieving adaptive goal-tracking behaviors with changing goals, and a central pattern generator (CPG) system with Matsuoka oscillators for generating stable and diverse locomotion patterns. The two modules are interconnected into a closed-loop system: The RL module, analogizing the locomotion region located in the midbrain of vertebrate animals, regulates the input to the CPG system given state feedback from the robot. The output of the CPG system is then translated into pressure inputs to the pneumatic actuators of the soft snake robot. Based on the fact that the oscillation frequency and wave amplitude of the Matsuoka oscillator can be independently controlled under different time scales, we further adapt the option-critic framework to improve the learning performance measured by optimality and data efficiency. The performance of the proposed controller is experimentally validated with both simulated and real soft snake robots.  more » « less
Award ID(s):
1728412
NSF-PAR ID:
10301484
Author(s) / Creator(s):
; ; ; ;
Date Published:
Journal Name:
2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Page Range / eLocation ID:
7758 to 7765
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Snake robotics is an important research topic with a wide range of applications, including inspection in confined spaces, search-and-rescue, and disaster response. Snake robots are well-suited to these applications because of their versatility and adaptability to unstructured and constrained environments. In this paper, we introduce a soft pneumatic robotic snake that can imitate the capabilities of biological snakes, its soft body can provide flexibility and adaptability to the environment. This paper combines soft mobile robot modeling, proprioceptive feedback control, and motion planning to pave the way for functional soft robotic snake autonomy. We propose a pressure-operated soft robotic snake with a high degree of modularity that makes use of customized embedded flexible curvature sensing. On this platform, we introduce the use of iterative learning control using feedback from the on-board curvature sensors to enable the snake to automatically correct its gait for superior locomotion. We also present a motion planning and trajectory tracking algorithm using an adaptive bounding box, which allows for efficient motion planning that still takes into account the kinematic state of the soft robotic snake. We test this algorithm experimentally, and demonstrate its performance in obstacle avoidance scenarios. 
    more » « less
  2. The locomotion of soft snake robots is dependent on frictional interactions with the environment. Frictional anisotropy is a morphological characteristic of snakeskin that allows snakes to engage selectively with surfaces and generate propulsive forces. The prototypical slithering gait of most snakes is lateral undulation, which requires a significant lateral resistance that is lacking in artificial skins of existing soft snake robots. We designed a set of kirigami lattices with curvilinearly-arranged cuts to take advantage of in-plane rotations of the 3D structures when wrapped around a soft bending actuator. By changing the initial orientation of the scales, the kirigami skin produces high lateral friction upon engagement with surface asperities, with lateral to cranial anisotropic friction ratios above 4. The proposed design increased the overall velocity of the soft snake robot more than fivefold compared to robots without skin. 
    more » « less
  3. Conventional catheter- or probe-based in vivo biomedical sensing is uncomfortable, inconvenient, and sometimes infeasible for longterm monitoring. Existing implantable sensors often require an invasive procedure for sensor placement. Untethered soft robots with the capability to deliver the sensor to the desired monitoring point hold great promise for minimally invasive biomedical sensing. Inspired by the locomotion modes of snakes, we present here a soft kirigami robot for sensor deployment and real-time wireless sensing. The locomotion mechanism of the soft robot is achieved by kirigami patterns that offer asymmetric tribological properties that mimic the skin of the snake. The robot exhibits good deployability, excellent load capacity (up to 150 times its own weight), high-speed locomotion (0.25 body length per step), and wide environmental adaptability with multimodal movements (obstacle crossing, locomotion in wet and dry conditions, climbing, and inverted crawling). When integrated with passive sensors, the versatile soft robot can locomote inside the human body, deliver the passive sensor to the desired location, and hold the sensor in place for real-time monitoring in a minimally invasive manner. The proof-of-concept prototype demonstrates that the platform can perform real-time impedance monitoring for the diagnosis of gastroesophageal reflux disease. 
    more » « less
  4. Synopsis Locomotion in most tetrapods involves coordinated efforts between appendicular and axial musculoskeletal systems, where interactions between the limbs and the ground generate vertical (GV), horizontal (GH), and mediolateral (GML) ground-reaction forces that are transmitted to the axial system. Snakes have a complete absence of external limbs and represent a fundamental shift from this perspective. The axial musculoskeletal system of snakes is their primary structure to exert, transmit, and resist all motive and reaction forces for propulsion. Their lack of limbs makes them particularly dependent on the mechanical interactions between their bodies and the environment to generate the net GH they need for forward locomotion. As organisms that locomote on their bellies, the forces that enable the various modes of snake locomotion involve two important structures: the integument and the ribs. Snakes use the integument to contact the substrate and produce a friction-reservoir that exceeds their muscle-induced propulsive forces through modulation of scale stiffness and orientation, enabling propulsion through variable environments. XROMM work and previous studies suggest that the serially repeated ribs of snakes change their cross-sectional body shape, deform to environmental irregularities, provide synergistic stabilization for other muscles, and differentially exert and transmit forces to control propulsion. The costovertebral joints of snakes have a biarticular morphology, relative to the unicapitate costovertebral joints of other squamates, that appears derived and not homologous with the ancestral bicapitate ribs of Amniota. Evidence suggests that the biarticular joints of snakes may function to buttress locomotor forces, similar to other amniotes, and provide a passive mechanism for resisting reaction forces during snake locomotion. Future comparisons with other limbless lizard taxa are necessary to tease apart the mechanics and mechanisms that produced the locomotor versatility observed within Serpentes. 
    more » « less
  5. Soft robotic snakes (SRSs) have a unique combination of continuous and compliant properties that allow them to imitate the complex movements of biological snakes. Despite the previous attempts to develop SRSs, many have been limited to planar movements or use wheels to achieve locomotion, which restricts their ability to imitate the full range of biological snake movements. We propose a new design for the SRSs that is wheelless and powered by pneumatics, relying solely on spatial bending to achieve its movements. We derive a kinematic model of the proposed SRS and utilize it to achieve two snake locomotion trajectories, namely side winding and helical rolling. These movements are experimentally evaluated under different gait parameters on our SRS prototype. The results demonstrate that the SRS can successfully mimic the proposed spatial locomotion trajectories. This is a significant improvement over the previous designs, which were either limited to planar movements or relied on wheels for locomotion. The ability of the SRS to effectively mimic the complex movements of biological snakes opens up new possibilities for its use in various applications. 
    more » « less