Reinforcement Learning from Wild Animal Videos

We propose to learn legged robot locomotion skills by watching thousands of wild animal videos from the internet, such as those featured in nature documentaries. Indeed, such videos offer a rich and diverse collection of plausible motion examples, which could inform how robots should move. To achieve this, we introduce Reinforcement Learning from Wild Animal Videos (RLWAV), a method to ground these motions into physical robots. We first train a video classifier on a large-scale animal video dataset to recognize actions from RGB clips of animals in their natural habitats. We then train a multi-skill policy to control a robot in a physics simulator, using the classification score of a third-person camera capturing videos of the robot's movements as a reward for reinforcement learning. Finally, we directly transfer the learned policy to a real quadruped Solo. Remarkably, despite the extreme gap in both domain and embodiment between animals in the wild and robots, our approach enables the policy to learn diverse skills such as walking, jumping, and keeping still, without relying on reference trajectories nor skill-specific rewards.

Parallel and Proximal Linear-Quadratic Methods for Real-Time Constrained Model-Predictive Control

-Recent strides in model predictive control (MPC)underscore a dependence on numerical advancements to efficientlyand accurately solve large-scale problems. Given the substantialnumber of variables characterizing typical whole-body optimalcontrol (OC) problems -often numbering in the thousands-exploiting the sparse structure of the numerical problem becomescrucial to meet computational demands, typically in the range ofa few milliseconds. A fundamental building block for computingNewton or Sequential Quadratic Programming (SQP) steps indirect optimal control methods involves addressing the linearquadratic regulator (LQR) problem. This paper concentrateson equality-constrained problems featuring implicit systemdynamics and dual regularization, a characteristic found inadvanced interior-point or augmented Lagrangian solvers. Here,we introduce a parallel algorithm designed for solving an LQRproblem with dual regularization. Leveraging a rewriting of theLQR recursion through block elimination, we first enhanced theefficiency of the serial algorithm, then subsequently generalized itto handle parametric problems. This extension enables us to splitdecision variables and solve multiple subproblems concurrently.Our algorithm is implemented in our nonlinear numerical optimalcontrol library ALIGATOR. It showcases improved performanceover previous serial formulations and we validate its efficacy bydeploying it in the model predictive control of a real quadrupedrobot. This paper follows up from our prior work on augmentedLagrangian methods for numerical optimal control with implicitdynamics and constraints.

CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learning

Deep Reinforcement Learning (RL) has demonstrated impressive results in solving complex robotic tasks such as quadruped locomotion. Yet, current solvers fail to produce efficient policies respecting hard constraints. In this work, we advocate for integrating constraints into robot learning and present Constraints as Terminations (CaT), a novel constrained RL algorithm. Departing from classical constrained RL formulations, we reformulate constraints through stochastic terminations during policy learning: any violation of a constraint triggers a probability of terminating potential future rewards the RL agent could attain. We propose an algorithmic approach to this formulation, by minimally modifying widely used off-the-shelf RL algorithms in robot learning (such as Proximal Policy Optimization). Our approach leads to excellent constraint adherence without introducing undue complexity and computational overhead, thus mitigating barriers to broader adoption. Through empirical evaluation on the real quadruped robot Solo crossing challenging obstacles, we demonstrate that CaT provides a compelling solution for incorporating constraints into RL frameworks. Videos and code are available at https://constraints-as-terminations.github.io.

Visually Guided Model Predictive Robot Control via 6D Object Pose Localization and Tracking

The objective of this work is to enable manipulation tasks with respect to the 6D pose of a dynamically moving object using a camera mounted on a robot. Examples include maintaining a constant relative 6D pose of the robot arm with respect to the object, grasping the dynamically moving object, or co-manipulating the object together with a human. Fast and accurate 6D pose estimation is crucial to achieve smooth and stable robot control in such situations. The contributions of this work are three fold. First, we propose a new visual perception module that asynchronously combines accurate learning-based 6D object pose localizer and a high-rate model-based 6D pose tracker. The outcome is a low-latency accurate and temporally consistent 6D object pose estimation from the input video stream at up to 120 Hz. Second, we develop a visually guided robot arm controller that combines the new visual perception module with a torque-based model predictive control algorithm. Asynchronous combination of the visual and robot proprioception signals at their corresponding frequencies results in stable and robust 6D object pose guided robot arm control. Third, we experimentally validate the proposed approach on a challenging 6D pose estimation benchmark and demonstrate 6D object pose-guided control with dynamically moving objects on a real 7 DoF Franka Emika Panda robot.

Perceptive Locomotion through Whole-Body MPC and Optimal Region Selection

Real-time synthesis of legged locomotion maneuvers in challenging industrial settings is still an open problem, requiring simultaneous determination of footsteps locations several steps ahead while generating whole-body motions close to the robot's limits. State estimation and perception errors impose the practical constraint of fast re-planning motions in a model predictive control (MPC) framework. We first observe that the computational limitation of perceptive locomotion pipelines lies in the combinatorics of contact surface selection. Re-planning contact locations on selected surfaces can be accomplished at MPC frequencies (50-100 Hz). Then, whole-body motion generation typically follows a reference trajectory for the robot base to facilitate convergence. We propose removing this constraint to robustly address unforeseen events such as contact slipping, by leveraging a state-of-the-art whole-body MPC (Croccodyl). Our contributions are integrated into a complete framework for perceptive locomotion, validated under diverse terrain conditions, and demonstrated in challenging trials that push the robot's actuation limits, as well as in the ICRA 2023 quadruped challenge simulation.

Optimization-Based Control for Dynamic Legged Robots

In a world designed for legs, quadrupeds, bipeds, and humanoids have the opportunity to impact emerging robotics applications from logistics, to agriculture, to home assistance. The goal of this survey is to cover the recent progress toward these applications that has been driven by model-based optimization for the real-time generation and control of movement. The majority of the research community has converged on the idea of generating locomotion control laws by solving an optimal control problem (OCP) in either a model-based or data-driven manner. However, solving the most general of these problems online remains intractable due to complexities from intermittent unidirectional contacts with the environment, and from the many degrees of freedom of legged robots. This survey covers methods that have been pursued to make these OCPs computationally tractable, with specific focus on how environmental contacts are treated, how the model can be simplified, and how these choices affect the numerical solution methods employed. The survey focuses on model-based optimization, covering its recent use in a stand alone fashion, and suggesting avenues for combination with learning-based formulations to further accelerate progress in this growing field.

Constrained Differential Dynamic Programming: A primal-dual augmented Lagrangian approach

Trajectory optimization is an efficient approach for solving optimal control problems for complex robotic systems. It relies on two key components: first the transcription into a sparse nonlinear program, and second the corresponding solver to iteratively compute its solution. On one hand, differential dynamic programming (DDP) provides an efficient approach to transcribe the optimal control problem into a finite-dimensional problem while optimally exploiting the sparsity induced by time. On the other hand, augmented Lagrangian methods make it possible to formulate efficient algorithms with advanced constraint-satisfaction strategies. In this paper, we propose to combine these two approaches into an efficient optimal control algorithm accepting both equality and inequality constraints. Based on the augmented Lagrangian literature, we first derive a generic primal-dual augmented Lagrangian strategy for nonlinear problems with equality and inequality constraints. We then apply it to the dynamic programming principle to solve the value-greedy optimization problems inherent to the backward pass of DDP, which we combine with a dedicated globalization strategy, resulting in a Newton-like algorithm for solving constrained trajectory optimization problems. Contrary to previous attempts of formulating an augmented Lagrangian version of DDP, our approach exhibits adequate convergence properties without any switch in strategies. We empirically demonstrate its interest with several case-studies from the robotics literature.

ProxNLP: a primal-dual augmented Lagrangian solver for nonlinear programming in Robotics and beyond

Mathematical optimization is the workhorse behind several aspects of modern robotics and control. In these applications, the focus is on constrained optimization, and the ability to work on manifolds (such as the classical matrix Lie groups), along with a specific requirement for robustness and speed. In recent years, augmented Lagrangian methods have seen a resurgence due to their robustness and flexibility, their connections to (inexact) proximal-point methods, and their interoperability with Newton or semismooth Newton methods. In the sequel, we present primal-dual augmented Lagrangian method for inequality-constrained problems on manifolds, which we introduced in our recent work, as well as an efficient C++ implementation suitable for use in robotics applications and beyond.

Estimating 3D Motion and Forces of Human-Object Interactions from Internet Videos

In this paper, we introduce a method to automatically reconstruct the 3D motion of a person interacting with an object from a single RGB video. Our method estimates the 3D poses of the person together with the object pose, the contact positions and the contact forces exerted on the human body. The main contributions of this work are three-fold. First, we introduce an approach to jointly estimate the motion and the actuation forces of the person on the manipulated object by modeling contacts and the dynamics of the interactions. This is cast as a large-scale trajectory optimization problem. Second, we develop a method to automatically recognize from the input video the 2D position and timing of contacts between the person and the object or the ground, thereby significantly simplifying the complexity of the optimization. Third, we validate our approach on a recent video+MoCap dataset capturing typical parkour actions, and demonstrate its performance on a new dataset of Internet videos showing people manipulating a variety of tools in unconstrained environments.

Solving Footstep Planning as a Feasibility Problem using L1-norm Minimization

One challenge of legged locomotion on uneven terrains is to deal with both the discrete problem of selecting a contact surface for each footstep and the continuous problem of placing each footstep on the selected surface. Consequently, footstep planning can be addressed with a Mixed Integer Program (MIP), an elegant but computationally-demanding method, which can make it unsuitable for online planning. We reformulate the MIP into a cardinality problem, then approximate it as a computationally efficient l1-norm minimisation, called SL1M. Moreover, we improve the performance and convergence of SL1M by combining it with a sampling-based root trajectory planner to prune irrelevant surface candidates. Our tests on the humanoid Talos in four representative scenarios show that SL1M always converges faster than MIP. For scenarios when the combinatorial complexity is small (< 10 surfaces per step), SL1M converges at least two times faster than MIP with no need for pruning. In more complex cases, SL1M converges up to 100 times faster than MIP with the help of pruning. Moreover, pruning can also improve the MIP computation time. The versatility of the framework is shown with additional tests on the quadruped robot ANYmal.