Shape-based compliant control with variable coordination centralization on a snake robot

Whitman, Julian; Ruscelli, Francesco; Travers, Matthew; Choset, Howie

doi:10.1109/cdc.2016.7799059

Cited by 21 publications

(25 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used the following empirically established optimal parameters for the compliant controller, with time step dt. The results of the compliant controller closely matches, or even slightly outperforms, previous results presented in [2], [3]. The results are compelling, as they show a distinct increase in the forward progression for the learned policy over the compliant controller.…”

Section: Experimental Validationsupporting

confidence: 83%

“…3) Decentralized Control: Decentralized control extends previous works on shape-based locomotion [2]. This previous work relies on the use of activation windows (i.e., groups of successive joints), and only couples the control of those joints covered by the same window, isolating them from other joints in the snake.…”

Section: A Background -Shape-based Compliant Control For Articulatedmentioning

confidence: 99%

“…We used an entropy-based loss function introduced in [39] to update the policy, π(a t | s t ; Ψ A ): 2 As mentioned in Section III-A3, the current shape of the snake robot influences the number and placement of the independent windows along its backbone. However, for the implementation of the decentralized controller, we cap the number of windows to 6.…”

Section: B Policy Representationmentioning

confidence: 99%

“…2) Experimental Results: To compare the efficacy of both controllers, we calculate the number of gait cycles needed to traverse one meter and the variance of this number over 15 trial runs, as established in [2]. This metric removes the potential variations due to running the gaits with differing temporal frequencies, thus only scoring the controller's kinematic abilities.…”

Section: Experimental Validationmentioning

confidence: 99%

See 3 more Smart Citations

Distributed Learning of Decentralized Control Policies for Articulated Mobile Robots

et al. 2019

Self Cite

View full text Add to dashboard Cite

State-of-the-art distributed algorithms for reinforcement learning rely on multiple independent agents, which simultaneously learn in parallel environments 1 while asynchronously updating a common, shared policy. Moreover, decentralized control architectures (e.g., CPGs) can coordinate spatially distributed portions of an articulated robot to achieve system-level objectives. In this work, we investigate the relationship between distributed learning and decentralized control by learning decentralized control policies for the locomotion of articulated robots in challenging environments. To this end, we present an approach that leverages the structure of the asynchronous advantage actorcritic (A3C) algorithm to provide a natural means of learning decentralized control policies on a single articulated robot. Our primary contribution shows individual agents in the A3C algorithm can be defined by independently controlled portions of the robot's body, thus enabling distributed learning on a single robot for efficient hardware implementation. We present results of closed-loop locomotion in unstructured terrains on a snake and a hexapod robot, using decentralized controllers learned offline and online respectively, as a natural means to cover the different key applications of our approach. For the snake robot, we are optimizing the forward progression in unstructured environments, but for the hexapod robot, the goal is to maintain a stabilized body pose. Our results show that the proposed approach can be adapted to many different types of articulated robots by controlling some of their independent parts in a distributed manner, and the decentralized policy can be trained with high sample efficiency.

show abstract

Section: Experimental Validationsupporting

confidence: 83%

Section: A Background -Shape-based Compliant Control For Articulatedmentioning

confidence: 99%

Section: B Policy Representationmentioning

confidence: 99%

Section: Experimental Validationmentioning

confidence: 99%

See 2 more Smart Citations

Distributed Learning of Decentralized Control Policies for Articulated Mobile Robots

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…In particular, these shape functions were used to capture joint-to-joint coupling and provide an intuitive set of controllable parameters that adapt the system to the environment in real-time. This approach was later extended to the definition of spatial frequency and temporal phase serpenoid shape parameters [48]. This approach provides a way to intuitively adapt the shape of highly articulated robots using joint-level torque feedback control, allowing a robot to navigate its way autonomously through unknown, irregular environment scenarios.…”

Section: Obstacle-aided Locomotionmentioning

confidence: 99%

Perception-Driven Obstacle-Aided Locomotion for Snake Robots: The State of the Art, Challenges and Possibilities †

et al. 2017

View full text Add to dashboard Cite

In nature, snakes can gracefully traverse a wide range of different and complex environments. Snake robots that can mimic this behaviour could be fitted with sensors and transport tools to hazardous or confined areas that other robots and humans are unable to access. In order to carry out such tasks, snake robots must have a high degree of awareness of their surroundings (i.e., perception-driven locomotion) and be capable of efficient obstacle exploitation (i.e., obstacle-aided locomotion) to gain propulsion. These aspects are pivotal in order to realise the large variety of possible snake robot applications in real-life operations such as fire-fighting, industrial inspection, search-and-rescue, and more. In this paper, we survey and discuss the state of the art, challenges, and possibilities of perception-driven obstacle-aided locomotion for snake robots. To this end, different levels of autonomy are identified for snake robots and categorised into environmental complexity, mission complexity, and external system independence. From this perspective, we present a step-wise approach on how to increment snake robot abilities within guidance, navigation, and control in order to target the different levels of autonomy. Pertinent to snake robots, we focus on current strategies for snake robot locomotion in the presence of obstacles. Moreover, we put obstacle-aided locomotion into the context of perception and mapping. Finally, we present an overview of relevant key technologies and methods within environment perception, mapping, and representation that constitute important aspects of perception-driven obstacle-aided locomotion.

show abstract

Design and Development of a Wheel-less Snake Robot with Active Stiffness Control for Adaptive Pedal Wave Locomotion

et al. 2019

View full text Add to dashboard Cite

This paper presents the design and manufacture process of a wheel-less, modular snake robot with Series Elastic Actuators to reliably measure motor torque signal and investigate the effectiveness of active stiffness control for achieving adaptive snake-like locomotion. A Polyurethane based elastic element to be attached between the motor and the links at each joint has been designed and manufactured using water jet cutter, which made the final design easier to develop and more cost-effective, compared to existing snake robots with torque measurement capabilities. The reliability of such torque measurement mechanism examined using simulated dynamical model of pedal wave motion, which proved the efficacy of the design. A distributed control system is also designed, which with the help of an admittance controller, enables active control of the joint stiffness to achieve adaptive snake robot pedal wave locomotion to climb over obstacles, which unlike existing methods does not require prior information about the location of the obstacle. The effectiveness of the proposed controller in comparison to open-loop control strategy has been shown by the number of experiments, which showed the capability of the robot to successfully climb over obstacles with the height of more than 55% of the diameter of the snake robot modules.

show abstract

Shape-based compliant control with variable coordination centralization on a snake robot

Cited by 21 publications

References 15 publications

Distributed Learning of Decentralized Control Policies for Articulated Mobile Robots

Distributed Learning of Decentralized Control Policies for Articulated Mobile Robots

Perception-Driven Obstacle-Aided Locomotion for Snake Robots: The State of the Art, Challenges and Possibilities †

Design and Development of a Wheel-less Snake Robot with Active Stiffness Control for Adaptive Pedal Wave Locomotion

Contact Info

Product

Resources

About