Bioinspired pursuit with a swimming robot using feedback control of an internal rotor

Free, Brian A; Lee, Jinseong; Paley, Derek A.

doi:10.1088/1748-3190/ab745e

Cited by 13 publications

(13 citation statements)

References 48 publications

(79 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Prior work has established that the Chaplygin-sleigh model exhibits limit-cycle dynamics under open-loop periodic control inputs (Pollard et al, 2019), as well as feedback control (Lee et al, 2019) (Free et al, 2020). Consider the feedback control (Lee et al, 2019)…”

Section: Chaplygin Sleigh Dynamicsmentioning

confidence: 99%

Planar Formation Control of a School of Robotic Fish: Theory and Experiments

Paley¹,

Thompson²,

Wolek³

et al. 2021

Front. Control Eng.

View full text Add to dashboard Cite

This paper presents a nonlinear control design for the stabilization of parallel and circular motion in a school of robotic fish actuated with internal reaction wheels. The closed-loop swimming dynamics of the fish robots are represented by the canonical Chaplygin sleigh. They exchange relative state information according to a connected, undirected communication graph to form a system of coupled, nonlinear, second-order oscillators. Prior work on collective motion of constant-speed, self-propelled particles serves as the foundation of our approach. However, unlike a self-propelled particle, the fish robots follow limit-cycle dynamics to sustain periodic flapping for forward motion with time-varying speed. Parallel and circular motions are achieved in an average sense without feedback linearization of the agents’ dynamics. Implementation of the proposed parallel formation control law on an actual school of soft robotic fish is described, including system identification experiments to identify motor dynamics and the design of a motor torque-tracking controller to follow the formation torque control. Experimental results demonstrate a school of four robotic fish achieving parallel formations starting from random initial conditions.

show abstract

Section: Chaplygin Sleigh Dynamicsmentioning

confidence: 99%

Planar Formation Control of a School of Robotic Fish: Theory and Experiments

Paley¹,

Thompson²,

Wolek³

et al. 2021

Front. Control Eng.

View full text Add to dashboard Cite

show abstract

“…The locomotion of fish and other aquatic swimmers has many desirable characteristics such as energy efficiency, agility, and stealth [1][2][3][4] , which have inspired the design of many biomimetic robots. Designs for fish-like robots include those that are assemblages, rigid links actuated by motors imitating the motion of tails and fins 5 , motor-driven flexible links 6,7 , elongated snake and eel like robots 8,9 , soft robots making use of dielectric elastomers, electroactive polymers or fluidic elastomer actuators [10][11][12][13][14] , or robots with internal reaction wheels 15,16 . In all such designs, the small size of the fish-like robots and the resulting constraints on actuation and power require that the robots harness the fluid structure and fluidstructure interaction for efficient and agile motion.…”

Section: Introductionmentioning

confidence: 99%

“…The swimming robot in this paper is modeled as a free swimming Joukowski hydrofoil, propelled and steered by an internal reaction wheel 15,16 . A particularly simple surrogate model that emulates the dynamics of such a swimmer is a nonholonomic system known as the Chaplygin sleigh.…”

Section: Introductionmentioning

confidence: 99%

“…Analytical approximations for these limit cycles and as a function of the forcing frequency and amplitude of the torque and the inverse dynamics problem of finding the periodic torque to generate a limit cycle have been shown in 42 . Torques for steering the Chaplygin sleigh 16,42 and path tracking for the Chaplygin sleigh using a vector pursuit method were demonstrated in 43 . Since we are interested in transfer learning using the low-dimensional model of the Chaplygin sleigh, we revisit this problem of simultaneous velocity tracking and steering using a reinforcement learning framework.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Physics-Informed Reinforcement Learning for Motion Control of a Fish-like Swimming Robot

Rodwell

Tallapragada

2022

Preprint

View full text Add to dashboard Cite

Motion control of fish-like swimming robots presents many challenges due to the unstructured environment and un-modelled governing physics of the fluid-robot interaction. Commonly used low-fidelity control models using simplified formulas for drag and lift force do not capture key physics that can play an important role in the dynamics of small-sized robots with limited actuation. Deep Reinforcement Learning (DRL) holds considerable promise for motion control of robots with complex dynamics. Reinforcement learning methods require large amounts of data exploring a large subset of the relevant state space, which can be expensive, time consuming or unsafe to obtain. Data from simulations can be used in the initial stages of DRL, but in the case of swimming robots, large numbers of simulations are also infeasible from a time and computational resources perspective. Surrogate models that capture the primary physics of the system can be a useful starting point for training a DRL agent which is subsequently transferred to train with a higher fidelity simulation. We demonstrate the utility of such physics-informed reinforcement learning to train a policy that can enable velocity and path tracking for a planar swimming (fish-like) rigid Joukowski hydrofoil. This is done through a curriculum where the DRL agent is first trained to track limit cycles in a velocity space for a representative nonholonomic system and then transferred to to train on a small simulation data set of the swimmer. The results show the utility of physics-informed reinforcement learning for the control of fish-like swimming robots.

show abstract

“…Planktonic microorganisms inhabit a low-Reynolds-number environment and have antennae and setae to sense hydrodynamic signals produced by predators and preys [8,9]. Bioinspired mechanosensors that can sense the hydrodynamic fields are used in underwater robots employed for search and recovery, surveillance and ship inspection [10,11]. Thus, understanding how to exploit hydrodynamic cues is of interest both for mechanistic explanations of animal behavior and for underwater robotics.…”

mentioning

confidence: 99%

Reinforcement learning for pursuit and evasion of microswimmers at low Reynolds number

et al. 2022

View full text Add to dashboard Cite

Aquatic organisms can use hydrodynamic cues to navigate, find their preys and escape from predators. We consider a model of two competing microswimmers engaged in a pursue-evasion task while immersed in a low-Reynolds-number environment. The players have limited abilities: they can only sense hydrodynamic disturbances, which provide some cue about the opponent's position, and perform simple manoeuvres. The goal of the pursuer is to capture the evader in the shortest possible time. Conversely the evader aims at deferring capture as much as possible. We show that by means of Reinforcement Learning the players find efficient and physically explainable strategies which non-trivially exploit the hydrodynamic environment. This Letter offers a proof-of-concept for the use of Reinforcement Learning to discover prey-predator strategies in aquatic environments, with potential applications to underwater robotics.

show abstract

Bioinspired pursuit with a swimming robot using feedback control of an internal rotor

Cited by 13 publications

References 48 publications

Planar Formation Control of a School of Robotic Fish: Theory and Experiments

Planar Formation Control of a School of Robotic Fish: Theory and Experiments

Physics-Informed Reinforcement Learning for Motion Control of a Fish-like Swimming Robot

Reinforcement learning for pursuit and evasion of microswimmers at low Reynolds number

Contact Info

Product

Resources

About