Abstract:
Achieving human and animal-level agility has been a long-standing goal in robotics research. Recent advancements in numerical optimization and machine learning have pushed legged systems to greater capabilities than ever before, enabling black flips, parkour, and manipulation of heavy objects. Despite these exciting developments, this thesis identifies two key limitations of current legged robot technology and aims to improve upon existing art.
First, legged robots today require manual specifications of desired behaviors and fail to learn from their human and animal counterparts. We introduce SLoMo, a first-of-its-kind framework for transferring skilled motions from casually captured videos of humans and animals to legged robots. From a monocular RGB video, SLoMo synthesizes physically plausible trajectories for downstream offline trajectory optimization and online predictive control of quadruped or humanoid robots. We demonstrate SLoMo by transferring cat and dog motions to quadruped robot hardware and human motions to a simulated humanoid robot.
Second, current model-predictive control (MPC) for legged systems often resort to simplified models due to computational limitations in real-time settings. This is due to the high dimensionality of these robots and the reliance of existing numerical optimization algorithms on fundamentally serial, CPU-friendly linear algebra routines. We leverage advancements in GPU parallelization by developing a quadratic programming (QP) solver that uses only GPU-friendly operations. We refer to our solver as ReLU-QP, thanks to its computational similarities to inferencing a deep neural network with rectified linear unit (ReLU) activation functions. Across benchmarks on solving random QPs and high-dimensional MPC tasks in simulation, including balancing a full-order Atlas humanoid robot on one foot under control limits, ReLU-QP shows an order-of-magnitude speed improvement over state-of-the-art CPU-based QP solvers and solves MPC for modern legged robots at kilohertz rates.
Abstract:
This thesis introduces the concept of TEXterity (Tactile Extrinsic deXterity) to address challenges in robotic manipulation. Focusing on tactile sensing, TEXterity aims to enhance dexterity by enabling robots to perceive and act upon extrinsic contact between the grasped object and the environment. Identifying interpretability, observability, and uncertainty as key challenges in tactile sensing, this thesis sets out to answer four pivotal questions:
The conclusion summarizes the key findings, emphasizing the significance of tactile sensing and TEXterity in addressing challenges and advancing robotic manipulation. Strategies to tackle major challenges are outlined, focusing on interpretability, observability, and uncertainty. In essence, this thesis lays the groundwork for unlocking the potential of tactile sensing in robotic manipulation, offering insights, solutions, and avenues for future research to propel the field toward achieving TEXterity and further toward human-level dexterity.
- 2nd Edition -
2024 IEEE International Conference on Robotics and Automation in PACIFICO Yokohama
Robotic technology has proven to be an excellent solution for aiding humans in an ever-increasing number of scenarios: from domestic and urban routines to industrial tasks, robots reduce the workload burden on humans and their exposure to hazards. Despite the capabilities demonstrated in recent years, many obstacles remain to be overcome. New challenges arise from the increasing capabilities of advanced robotic platforms. The more complex and unstructured the environment, the more robots should be versatile and reliable to overcome obstacles, plan optimal motions, and reliably accomplish the designed tasks.
Prof. Harry Asada Massachusetts Institute of Technology Department of Mechanical Engineering Fall 2020 All of the lecture recordings, slides, and notes are available on our lab website: External Link
Abstract:
Differentiable simulators promise faster computa- tion time for reinforcement learning by replacing zeroth-order gradient estimates of a stochastic objective with an estimate based on first-order gradients. However, it is yet unclear what fac- tors decide the performance of the two estimators on complex landscapes that involve long-horizon planning and control on physical systems, despite the crucial relevance of this question for the util- ity of differentiable simulators. We show that characteristics of certain physical systems, such as stiffness or discontinuities, may compromise the efficacy of the first-order estimator, and ana- lyze this phenomenon through the lens of bias and variance. We additionally propose an Ξ±-order gra- dient estimator, with Ξ± β [0, 1], which correctly utilizes exact gradients to combine the efficiency of first-order estimates with the robustness of zero- order methods. We demonstrate the pitfalls of traditional estimators and the advantages of the Ξ±-order estimator on some numerical examples.
Abstract:
Designing robots with extreme performance in a given task has long been an exciting research problem drawing attention from researchers in robotics, graphics, and artificial intelligence. As a robot is a combination of its hardware and software, an optimal robot requires both an excellent implementation of its hardware (e.g., morphological, topological, and geometrical designs) and an outstanding design of its software (e.g., perception, planning, and control algorithms). While we have seen promising breakthroughs for automating a robot's software design with the surge of deep learning in the past decade, exploration of optimal hardware design is much less automated and is still mainly driven by human experts, a process that is both labor-intensive and error-prone. Furthermore, experts typically optimize a robot's hardware and software separately, which may miss optimal designs that can only be revealed by optimizing its hardware and software simultaneously. This thesis argues that it is time to rethink robot design as a holistic process where a robot's body and brain should be co-optimized jointly and automatically. In this thesis, we present a computational robot design pipeline with differentiable simulation as a key player. We first introduce the concept of computational robot design on a real-world copter whose geometry and controller are co-optimized with a differentiable simulator, resulting in a custom copter that outperforms designs suggested by human experts by a substantial margin. Next, we push the boundary of differentiable simulation by developing advanced differentiable simulators for soft-body and fluid dynamics. Contrary to traditional belief, we show that deriving gradients for such intricate, high-dimensional physics systems can be both science and art. Finally, we discuss challenges in transferring computational designs discovered in simulation to real-world hardware platforms. We present a solution to this simulation-to-reality transfer problem using our differentiable simulator on an example of modeling and controlling a real-world soft underwater robot. We conclude this thesis by discussing open research directions in differentiable simulation and envisioning a fully automated computational design pipeline for real-world robots in the future.
2022, the year when I defended my Thesis, βMulti-body modeling of robot dynamics and system identification during MPCβ, in Scientific Computing. The updated translation of the poem can be found here.
Abstract
Due to external influences over parameters that characterize dynamical systems, an online parameter estimation must be added as part of model predictive control strategies. In this thesis, we show how continuous parameters estimation, using inverse dynamics, can be used for identifying the inertial parameters (mass, inertia, and center of mass) of multi-body systems as part of an adaptive control strategy. For this, a Featherstone spatial algebra equivalent model, based on screw theory was used. The system identification was done using a linear least squares approach using the Recursive Newton-Euler Algorithm as a way of implementing a generic solution. The process is for open-loop robots and is tested using an optimal control algorithm based on multiple shooting.
This four-day intensive course aims to provide both theoretical background and hands-on practical knowledge in formulating and numerical methods to solve optimal control problems with nonsmooth differential equation models with switches and state jumps. Nonsmooth dynamical systems arise in robotics, chemical engineering, biology, mechatronics, or aerospace, as soon as some if-else statements, switches, and state jump are encoded in the systemsβ dynamics. For example, contacts and friction in robotic systems lead to jumps and switches.
