SIMBICON: simple biped locomotion control

By KangKang Yin, Kevin Loken, Michiel van de Panne. ACM Transactions on Graphics, 2007

586 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/221472c2fa00a5f7ff5400c60ffddc928e50cab8

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

Legged Locomotion in Challenging Terrains using Egocentric Vision (2022, methodology): “Several classical works use model based techniques, or define heuristic reactive controllers to achieve the task of walking [19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31].”
DeepMimic (2018, methodology): “Model-based methods for tracking reference motions have also been demonstrated for locomotion with 3D humanoid characters [Lee et al. 2010a; Muico et al. 2009; Yin et al. 2007].”
Interactive Control of Diverse Complex Characters with Neural Networks (2015, unknown): “For example, for biped location common approaches include state machines and use of simplified models (such as the inverted pendulum) and concepts (such as zero moment or capture points) [21, 18].”
Models, feedback control, and open problems of 3D bipedal robotic walking (2014, background): “Heuristics for maintaining stability on slight inclines were studied in [90], and for more aggressive ground variations in [71, 82, 175, 75, 176, 38, 225].”
RMA: Rapid Motor Adaptation for Legged Robots (2021, methodology): “Conventionally, legged locomotion has been approached by using control-based methods [35, 42, 16, 54, 48, 25, 27, 2, 23, 4].”
Guided Policy Search (2013, methodology): “To illustrate the capacity of our method to learn from demonstration, the initial example trajectory for the walker was obtained from a prior locomotion system (Yin et al., 2007), while the 3D humanoid was initialized with example motion capture of human running.”
Capturability-based analysis and control of legged locomotion, Part 1: Theory and application to three simple gait models (2011, methodology): “This simple stepping strategy was used to create a variety of stable locomotion patterns in simulation [45,62] and was also found to be a good predictor of stable foot placement locations in the analysis of human walking [15,18,30,53].”
Fluid directed rigid body control using deep reinforcement learning (2018, methodology): “Such techniques have been used to control low-DOF dynamic systems, including articulated characters [Wang et al. 2012; Yin et al. 2007].”
Variational Policy Search via Trajectory Optimization (2013, unknown): “Following previous work [10], the trajectory for the walker was initialized with a demonstration from a hand-crafted locomotion system [22].”
Capturability-based analysis and control of legged locomotion, Part 2: Application to M2V2, a lower-body humanoid (2012, methodology): “Some of these capture point-based control methods were also implemented on a real 12 DoF robot [21].”
Exploring Deep and Recurrent Architectures for Optimal Control (2013, methodology): “with simple, linear policies, leading to the popularity of compact, specialized, and control-specific function approximators that lack the expressive power of large neural networks [8, 22].”
Dynamic Balance Force Control for compliant humanoid robots (2010, background): “Often this is handled by special consideration of the hip joint torque [12].”
Learning Complex Neural Network Policies with Trajectory Optimization (2014, methodology): “The initial trajectory for the swimmer was generated with unconstrained trajectory optimization using DDP, while the initial walking trajectory used a demonstration from a hand-crafted locomotion system (Yin et al., 2007), following our prior work (Levine & Koltun, 2013a).”
Learning Agile Robotic Locomotion Skills by Imitating Animals (2020, background): “The development of controllers for legged locomotion has been an enduring subject of interest in robotics, with a large body of work proposing a variety of control strategies for legged systems [37, 49, 54, 20, 18, 64, 8, 3].”