In this paper, we present Salamandra robotica II: an amphibious salamander robot that is able to walk and swim. The robot has four legs and an actuated spine that allow it to perform anguilliform swimming in water and walking on the ground. The paper first presents the new robot hardware design, which is an improved version of Salamandra robotica I. We then address several questions related to body-limb coordination in robots and animals that have a sprawling posture like salamanders and lizards, as opposed to the erect posture of mammals (e.g., in cats and dogs). In particular, we investigate how the speed of locomotion and curvature of turning motions depend on various gait parameters such as the body-limb coordination, the type of body undulation (offset, amplitude, and phase lag of body oscillations), and the frequency. Comparisons with animal data are presented, and our results show striking similarities with the gaits observed with real salamanders, in particular concerning the timing of the body's and limbs' movements and the relative speed of locomotion.

An important problem in the control of locomotion of robots with multiple degrees of freedom (e.g., biomimetic robots) is to adapt the locomotor patterns to the properties of the environment. This article addresses this problem for the locomotion of an amphibious snake robot, and aims at identifying fast swimming and crawling gaits for a variety of environments. Our approach uses a locomotion controller based on the biological concept of central pattern generators (CPGs) together with a gradient-free optimization method, Powell's method. A key aspect of our approach is that the gaits are optimized online, i.e., while moving, rather than as an off-line optimization process. We present various experiments with the real robot and in simulation: swimming, crawling on horizontal ground, and crawling on slopes. For each of these different situations, the optimized gaits are compared with the results of systematic explorations of the parameter space. The main outcomes of the experiments are: 1) optimal gaits are significantly different from one medium to the other; 2) the optimums are usually peaked, i.e., speed rapidly becomes suboptimal when the parameters are moved away from the optimal values; 3) our approach finds optimal gaits in much fewer iterations than the systematic search; and 4) the CPG has no problem dealing with the abrupt parameter changes during the optimization process. The relevance for robotic locomotion control is discussed.

This article presents a control architecture for controlling the locomotion of an amphibious snake/lamprey robot capable of swimming and serpentine locomotion. The control architecture is based on a central pattern generator (CPG) model inspired from the neural circuits controlling locomotion in the lamprey's spinal cord. The CPG model is implemented as a system of coupled nonlinear oscillators on board of the robot. The CPG generates coordinated travelling waves in real time while being interactively modulated by a human-operator. Interesting aspects of the CPG model include (1) that it exhibits limit cycle behavior (i.e. it produces stable rhythmic patterns that are robust against perturbations), (2) that the limit cycle behavior has a closed-form solution which provides explicit control over relevant characteristics such as frequency, amplitude and wavelength of the travelling waves, and (3) that the control parameters of the CPG can be continuously and interactively modulated by a human operator to offer high maneuverability. We demonstrate how the CPG allows one to easily adjust the speed and direction of locomotion both in water and on ground while ensuring that continuous and smooth setpoints are sent to the robot's actuated joints.

We present AmphiBot I, an amphibious snake robot capable of crawling and swimming. Experiments have been carried out to characterize how the speed of locomotion depends on the frequencies, amplitudes, and phase lags of undulatory gaits, both in water and on ground. Using this characterization, we can identify the fastest gaits for a given medium. Results show that the fastest gaits are different from one medium to the other, with larger optimal regions in parameter space for the crawling gaits. Swimming gaits are faster than crawling gaits for the same frequencies. For both media, the fastest locomotion is obtained with total phase lags that are smaller than one. These results are compared with data from fishes and from amphibian snakes.