A Framework for Extreme Locomotion Planning

Autor

Publicación en congreso

Idioma

A person practicing parkour is an incredible display of intelligent planning; he must reason carefully about his velocity and contact placement far into the future in order to locomote quickly through an environment. We seek to develop planners that will enable robotic systems to replicate this performance. An ideal planner can learn from examples and formulate feasible full-body plans to traverse a new environment. The proposed approach uses momentum equivalence to reduce the full-body system into a simplified one. Lowdimensional trajectory primitives are then composed by a sampling planner called Sampled Composition A* to produce candidate solutions that are adjusted by a trajectory optimizer and mapped to a full-body robot. Using primitives collected from a variety of sources, this technique is able to produce solutions to an assortment of simulated locomotion problems

URL

Terrain Runner: Control, Parameterization, Composition, and Planning for Highly Dynamic Motions

Autor

Publicación en congreso

Idioma

In this paper we learn the skills required by real-time physics-based avatars to perform parkour-style fast terrain crossing using a mix of running, jumping, speed-vaulting, and drop-rolling. We begin with a single motion capture example of each skill and then learn reduced-order linear feedback control laws that provide robust execution of the motions during forward dynamic simulation. We then parameterize each skill with respect to the environment, such as the height of obstacles, or with respect to the task parameters, such as running speed and direction. We employ a continuation process to achieve the required parameterization of the motions and their affine feedback laws. The continuation method uses a predictor-corrector method based on radial basis functions. Lastly, we build control laws specific to the sequential composition of different skills, so that the simulated character can robustly transition to obstacle clearing maneuvers from running whenever obstacles are encountered. The learned transition skills work in tandem with a simple online step-based planning algorithm, and together they robustly guide the character to achieve a state that is well-suited for the chosen obstacle-clearing motion.

URL

Enabling Smart Workflows over Heterogeneous ID-SensingTechnologies

Autor

Artículo de revista

Idioma

Sensing technologies in mobile devices play a key role in reducing the gapbetween the physical and the digital world. The use of automatic identification capabilitiescan improve user participation in business processes where physical elements are involved(Smart Workflows). However, identifying all objects in the user surroundings does notautomatically translate into meaningful services to the user. This work introduces Parkour,an architecture that allows the development of services that match the goals of each ofthe participants in a smart workflow. Parkour is based on a pluggable architecture thatcan be extended to provide support for new tasks and technologies. In order to facilitatethe development of these plug-ins, tools that automate the development process are alsoprovided. Several Parkour-based systems have been developed in order to validate theapplicability of the proposal.

URL

The simplest parkour model: Experimental validation and stability analysis

Autor

Artículo de revista

Idioma

We describe and experimentally validate the Simplest Parkour Model (SPM) for the ParkourBot, a planar dynamic climbing robot equipped with two springy BowLegs. By controlling the leg angles and injected energy at impact, the ParkourBot is capable of climbing up and down in a rigid chute on an inclined air table. The SPM consists of a point mass and two massless legs. The legs are assumed to be infinitely stiff, resulting in an instantaneous stance phase and a closed-form solution of the hybrid dynamics. In this paper, we show that the SPM is a good predictor of the actual experimental behavior. Using the SPM we compute the fixed points, stability and basins of attraction of period-1 limit cycles.

URL

Feedback control experiments with the parkourbot

Autor

artículo de revista

Idioma

The ParkourBot is a planar dynamic climbing biped robot and is capable of dynamically locomoting between two "vertical" walls in a reduced-gravity planar environment of an inclined air table. During flight, springy legs are compressed to store elastic energy. At impact, this potential energy is quickly converted to kinetic energy. In this paper, we demonstrate that simple feedback control strategies with a high-speed vision system can be used to control the Parkour-Bot to bounce in place, climb up and climb down

URL

Ecoextreme: Red eco-deportiva de los cerros orientales para el desarrollo recreativo, turístico y educativo de Bogotá

Autor

Trabajo Fin de Grado/Máster o similar

Idioma

Proyecto de espacio público y equipamiento deportivo para responder a la práctica de deportes extremos en la ciudad de Bogotá y beneficiar a la ciudadanía en general. El proyecto contempla los elementos de la estructura ecológica principal de los cerros orientales, elementos de la movilidad y del espacio público como elementos ordenadores de la ciudad y considera de las nuevas dinámicas que giran en torno al deporte (los deportes extremos como una nueva forma de interactuar con el espacio), involucrando las poblaciones de interés como son las del ámbito educativo y turístico, teniendo en cuenta las poblaciones vulnerables que se encuentran ubicadas en los alrededores de la zona de intervención.

URL