Learning locomotion over rough terrain using terrain templates

By Mrinal Kalakrishnan, Jonas Buchli, Peter Pastor, Stefan Schaal. 2009

106 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

Overcoming Exploration in Reinforcement Learning with Demonstrations (2017, background): “BC has seen success in autonomous driving [5], [6], quadcopter navigation [7], locomotion [8], [9].”
Active learning from demonstration for robust autonomous navigation (2012, background): “As a result, learning cost or reward functions from demonstration has become popular in recent years [1], [2], [3], [4].”
Learning of grasp selection based on shape-templates (2013, methodology): “Recently, templates have been successfully used to encode local regions of terrains enabling a quadruped robot to choose good footholds (Kalakrishnan et al. 2009).”
Deep reinforcement learning for tensegrity robot locomotion (2016, methodology): “Robotic learning methods have previously produced successful policies for tasks such as locomotion for bipeds and quadrupeds [2], [3], [4], [5], [6], [7].”
Robot Parkour Learning (2023, methodology): “Classical modular methods rely on decoupled visual perception and control pipelines, where the elevation maps [75, 76, 77, 78, 79, 80, 81], traversability maps [82, 83, 84, 85], or state estimators [86, 87, 88, 89, 90, 91, 92, 93, 94, 95] are constructed as intermediate representations for downstrea”
Model learning for robot control: a survey (2011, methodology): “Model learning has been shown to be an efficient tool in a variety of scenarios, such as inverse dynamics control [105], inverse kinematics [124,162,52], robot manipulation [151,66], autonomous navigation [4] or robot locomotion [60].”
Goal-conditioned Imitation Learning (2019, background): “Learning from Demonstrations, or Imitation Learning (IL), is a well-studied ﬁeld in robotics [17, 18, 19].”
Legged Locomotion in Challenging Terrains using Egocentric Vision (2022, background): “The foothold feasibility scores can either be estimated 246 heuristically [56, 57, 8, 58, 59, 10, 60] or learned [61, 62, 63, 64, 65].”
Learning objective functions for manipulation (2013, background): “The sparse solutions generated as a result of L 1 regularization also allow for fast evaluation of the learnt cost functions [18].”
A Framework for Efficient Robotic Manipulation (2020, methodology): “BC has been successfully applied across diverse modalities including video games [35], autonomous navigation [36], [37], autonomous aviation [38], locomotion [39], [40], and manipulation [26], [28], [30], [41].”
Learning, planning, and control for quadruped locomotion over challenging terrain (2011, methodology): “The algorithm extracts discretized height maps of small patches of terrain of different scales, so-called terrain templates (Kalakrishnan et al. 2009).”