| Co-instructors | **Jehee Lee Jungnam Park** | | --- | --- | | Time | Tuesday & Thursday @ 14:00 - 15:15 | | Location | 302-106 |

Overview

이 과목은 사람과 동물의 움직임에 원리를 이해하고 이를 컴퓨터 시뮬레이션으로 재현하는데 관련된 기본 지식을 익히는 것을 목표로 합니다. 사람의 몸은 뼈와 근육, 힘줄 등 복잡한 해부학적 구조를 가지고 있고, 시각/청각/촉각 등의 감각 기능과 뇌에서의 사고 기능, 근육에서의 운동 기능이 신경망을 거친 복잡한 통신과정을 거쳐 움직임을 만들어냅니다. 필연적으로 생체 동작에 대한 연구는 다학제적 성격을 갖고, 의학, 생체역학, 인간공학, 신경과학, 스포츠과학, 머신러닝, 제어이론 등 다양한 분야의 융합을 통해서 이루어집니다.

이 과목은 대학원 세미나 과목으로 넓은 범위를 포괄하기 때문에 강의과 논문 세미나를 통한 토론이 혼합하여 이루어질 예정입니다. 수강생들은 자신에게 익숙한 분야 외에도 다양한 분야를 접하게 될 것입니다. 이 과목은 정해진 교재가 없이 매 시간마다 서로 다른 교재, 논문, 자료에 기반해서 강의가 진행될 예정입니다.

Grading Policy

Late policy

Students will be allowed a total of five late days per semester without penalty. Any work submitted late after the five late days have been used will be given an automatic zero on the assignment. Make sure to start early and complete your assignments on time. This policy will be enforced strictly.

Programming Assignment

Assignment #1 (Bipedal walking)

Assignment #2 (DRL with Reference Trajectory)[Last updated: 16:47 04/22]

Assignment #3 (DRL with Musculotendon)

Assignment Score [Updated 15:16 06/19]

Lecture Notes

https://drive.google.com/drive/folders/1CEaY_ZJbXTmh_ztLvr1uQwKxzI9uazoG?usp=sharing

Schedule

Week Date Programming assignment
1 Mar 4 Course introduction
Mar 6 Rigid body dynamics: Newton-Euler equations
2 Mar 11 Forward kinematics and its Jacobian
Mar 13 Articulated body dynamics: Euler-Langrange equation of motion
3 Mar 18 Handling ground reaction
Mar 20 Human balancing strategies
4 Mar 25 **Simplified models
▷** Kajita, et al. The 3D linear inverted pendulum mode: A simple modeling for a biped walking pattern generation, IROS 2001.
▷ Tsai, et al. Real-time physics-based 3D biped character animation using an inverted pendulum model, IEEE TVCG 2010.
▷ Kwon, et al. Fast and flexible multilegged locomotion using learned centroidal dynamics, SIGGRAPH 2020.
Mar 27 Control basics : P , PD and PID
5 Apr 1 Reinforcement Learning Basics #1 out #1 out
Apr 3 DRL with Reference Trajectory
6 Apr 8 Osteology and Myology (part I)
Apr 10 Osteology and Myology (part II)
7 Apr 15 Osteology and Myology (part III) #1 in, #2 out
Apr 17 Normal and pathological gait (part I)
▷ J. Perry, Gait Analysis: Normal and Pathological Functions, 1992.
8 Apr 22 Normal and pathological gait (part II)
Apr 24 Muscle Physiology
9 Apr 29 Midterm exam
May 1 Muscle Models
10 May 6 No class
May 8 DRL with Musculotendon Actuators #3 out
11 May 13 **Feedback Balance Control
▷** Hodgins et al. Animating human athletics, SIGGRAPH 1995.
▷ Yin et al. SIMBICON: Simple biped locomotion control, SIGGRAPH 2007.
May 15 **Trajectory Optimization Basics
▷** Witkin and Kass. Spacetime constraints, SIGGRAPH 1988.
▷ Sok et al. Simulating biped behaviors from human motion data, SIGGRAPH 2007. #2 in
12 May 20 **Trajectory Optimization with Fictional Force
▷** Kim et al. ViSA: Physics-based virtual stunt actors for ballistic stunts, SIGGRAPH 2025 (to appear)
▷ Mordatch et al. Discovery of complex behaviors through contact invariant optimization, SIGGRAPH 2012
▷ Han et al. Data-guided model predictive control based on smoothed contact dynamics, Eurographics 2016
▷ Hamalainen et al. Online motion synthesis using sequential monte carlo, SIGGRAPH 2014
May 22 **Optimality Principles
▷** Anderson and Pandy. A dynamic optimization solution for vertical jumping in three dimensions, Computer Methods in Biomechanical and Biomedical Engineering 1999
▷ Fang and Pollard. Efficient synthesis of physically valid human motion, SIGGRAPH 2003
▷ Lee et al. Scalable muscle-actuated human simulation and control, SIGGRAPH 2019
▷ Ackermann and van den Bogert. Optimality principles for model-based prediction of human gait, Journal of Biomechanics 2010.
13 May 27 Learning and Regression
▷ Sok et al. Simulating biped behaviors from human motion data, SIGGRAPH 2007.
▷ Ju et al. Data-driven control of flapping flight, ACM ToG 2013.
May 29 **Markov decision process
▷** Tao et al. Learning to get up, SIGGRAPH 2022.
14 Jun 3 No class
Jun 5 **Deep Q-Learning
▷** Mnih et al. Human-level control through deep reinforcement
learning, Nature 2015.
▷ Levine et al. Learning Complex Neural Network Policies with Trajectory Optimization, ICML 2014.
▷ Won et al. How to Train Your Dragon: Example-guided control of flapping flight, SIGGRAPH Asia 2017.
15 Jun 10 **Stochasticity in Optimization and Learning
▷** Wang et al. Optimizing walking controllers for uncertain inputs and environments, SIGGRAPH 2010.
▷ Peng et al. Learning agile robotic locomotion skills by imitating animals, RSS 2020.
▷ Lee et al. Learning a family of motor skills from a single motion clip, SIGGRAPH 2021. #3 in
Jun 12 Wrap up