Figure 3 - uploaded by Geoff Nitschke
Content may be subject to copyright.
Context in source publication
Context 1
... maps and failures were combined into the following experiment configurations (table 2). The robot in the physical environment shown in figure 3a was configured identically to the simulated environment shown in figure 3b. For each trial the gait performance was manually measured and fed back into the M-BOA algorithm. ...
Similar publications
Dans le cadre du programme Montréal en commun de la Ville de Montréal, notre équipe a mené une démarche d’évaluation participative avec quatre organisations du système alimentaire alternatif. Cette démarche, comprenant trois ateliers participatifs et des séances d’accompagnement, avait pour objectifs de développer des outils pour l’évaluation des p...
El presente recorrido pretende reconstruir la estructuración del sistema educativo provincial en Santiago del Estero en la segunda mitad del siglo XIX; desde la población escolar y los registros estadísticos del periodo demarcado, para posteriormente poder analizar los registros lingüísticos vinculados con la quichua y los debates que ello generó e...
Citations
... Furthermore, a multilegged mechanism usually responds to malfunction by selecting embedded recovery strategies or learning new recovery plans depending on its current state. Although both schemes have been studied widely during the last decade, researchers have often preferred using sample-based learning algorithms such as the ones based on gradients [8], evolutionary computing [9], [10], [11], [12], [13], [16], Bayesian optimization [14] and reinforcement learning [15]. ...
... The studies mentioned above rendered new learning-based adaptation strategies to respond to malfunction. For instance, recent studies have used vector-based representations of gait controllers [14], [16], enabling us to understand the search and constraint space of gait adaptation mechanisms when actuators in multilegged systems become malfunction. This paper explores the benefits of using an enumerative encoding strategy to render new gait adaptation strategies when legs in hexapods malfunction. ...
... Compared to conventional vector-based encodings [16], the factorial representation brings the potential of introducing canonicity and diversity concepts into the gradient-free optimization algorithms. ...
The quest for the efficient adaptation of multilegged robotic systems to changing conditions is expected to render new insights into robotic control and locomotion. In this paper, we study the performance frontiers of the enumerative (factorial) encoding of hexapod gaits for fast recovery to conditions of leg failures. Our computational studies using five nature-inspired gradient-free optimization heuristics have shown that it is possible to render feasible recovery gait strategies that achieve minimal deviation to desired locomotion directives with a few evaluations (trials). For instance, it is possible to generate viable recovery gait strategies reaching 2.5 cm. (10 cm.) deviation on average with respect to a commanded direction with 40 - 60 (20) evaluations/trials. Our results are the potential to enable efficient adaptation to new conditions and to explore further the canonical representations for adaptation in robotic locomotion problems.
... BO is a global optimiser that uses observations to form the posterior distribution over the objective function [38]. It has been widely used in robot control due to its sample efficiency [39], [40], [41]. ...
While quadruped robots usually have good stability and load capacity, bipedal robots offer a higher level of flexibility / adaptability to different tasks and environments. A multi-modal legged robot can take the best of both worlds. In this paper, we propose a multi-modal locomotion framework that is composed of a hand-crafted transition motion and a learning-based bipedal controller -- learnt by a novel algorithm called Automated Residual Reinforcement Learning. This framework aims to endow arbitrary quadruped robots with the ability to walk bipedally. In particular, we 1) design an additional supporting structure for a quadruped robot and a sequential multi-modal transition strategy; 2) propose a novel class of Reinforcement Learning algorithms for bipedal control and evaluate their performances in both simulation and the real world. Experimental results show that our proposed algorithms have the best performance in simulation and maintain a good performance in a real-world robot. Overall, our multi-modal robot could successfully switch between biped and quadruped, and walk in both modes. Experiment videos and code are available at https://chenaah.github.io/multimodal/.
In biological societies, complex interactions between the behavior and morphology of evolving organisms and their environment have given rise to a wide range of complex and diverse social structures. Similarly, in artificial counterparts such as swarm-robotics systems, collective behaviors emerge via the interconnected dynamics of robot morphology (sensory-motor configuration), behavior (controller), and environment (task). Various studies have demonstrated morphological and behavioral diversity enables biological groups to exhibit adaptive, robust, and resilient collective behavior across changing environments. However, in artificial (swarm robotic) systems there is little research on the impact of changing environments on morphological and behavioral (body-brain) diversity in emergent collective behavior, and the benefits of such diversity. This study uses evolutionary collective robotics as an experimental platform to investigate the impact of increasing task environment complexity (collective behavior task difficulty) on the evolution and benefits of morphological and behavioral diversity in robotic swarms. Results indicate that body-brain evolution using coupled behavior and morphology diversity maintenance yields higher behavioral and morphological diversity, which is beneficial for collective behavior task performance across task environments. Results also indicate that such behavioral and morphological diversity maintenance coupled with body-brain evolution produces neuro-morpho complexity that does not increase concomitantly with task complexity.
A vast number of applications for legged robots entail tasks in complex, dynamic environments. But these environments put legged robots at high risk for limb damage. This paper presents an empirical study of fault tolerant dynamic gaits designed for a quadrupedal robot suffering from a single, known ``missing'' limb. Preliminary data suggests that the featured gait controller successfully anchors a previously developed planar monopedal hopping template in the three-legged spatial machine. This compositional approach offers a useful and generalizable guide to the development of a wider range of tripedal recovery gaits for damaged quadrupedal machines.
While quadruped robots usually have good stability and load capacity, bipedal robots offer a higher level of flexibility / adaptability to different tasks and environments. A multi-modal legged robot can take the best of both worlds. In this paper, we propose a multi-modal locomotion framework that is composed of a hand-crafted transition motion and a learning-based bipedal controller - learnt by a novel algorithm called Automated Residual Reinforcement Learning. This framework aims to endow arbitrary quadruped robots with the ability to walk bipedally. In particular, we 1) design an additional supporting structure for a quadruped robot and a sequential multi-modal transition strategy; 2) propose a novel class of Reinforcement Learning algorithms for bipedal control and evaluate their performances in both simulation and the real world. Experimental results show that our proposed algorithms have the best performance in simulation and maintain a good performance in a real-world robot. Overall, our multi-modal robot could successfully switch between biped and quadruped, and walk in both modes.
This paper proposes a novel walk control for hexapod robots based on Follow-the-Contact-Point (FCP) gait control, which can reduce or increase the number of walking legs during walking. The FCP gait control is decentralized event-driven gait control for multi-legged robots. In order to adapt the FCP gait control to changing the number of walking legs, we first introduce locomotion flag for each leg and adjacent information between legs. Then, to implement the adjacent information, the transition conditions of the control algorithm of FCP gait control are improved. As a result, the control algorithm obtains the properties of deadlock-free and maintaining the support triangle. The effectiveness of the proposed control architecture is verified by experiments in which a hexapod robot changes the number of walking legs during walking and walks on rough terrain even when the number of walking legs is reduced.
