Advancements in robot learning for object manipulation have shown promising results, yet certain everyday objects remain challenging for robots to effectively interact with. This discrepancy arises from the fact that human-designed objects are optimized for human use rather than robot manipulation. To address this gap, we propose a framework to automatically design 3D printable adaptations that can be attached to hard-to-use objects, thus improving "robot ergonomics". Our learning-based framework formulates the adaptation design and control as a dual Markov decision process and is able to improve robot-object interactions for various robot end effectors and objects. We further validate our designs in the real world with a Franka Panda robot. Please see the supplementary video and https://object-adaptation.github.io for additional visualizations.

Reinforcement Learning (RL) has seen many recent successes for quadruped robot control. The imitation of reference motions provides a simple and powerful prior for guiding solutions towards desired solutions without the need for meticulous reward design. While much work uses motion capture data or hand-crafted trajectories as the reference motion, relatively little work has explored the use of reference motions coming from model-based trajectory optimization. In this work, we investigate several design considerations that arise with such a framework, as demonstrated through four dynamic behaviours: trot, front hop, 180 backflip, and biped stepping. These are trained in simulation and transferred to a physical Solo 8 quadruped robot without further adaptation. In particular, we explore the space of feed-forward designs afforded by the trajectory optimizer to understand its impact on RL learning efficiency and sim - to- real transfer. These findings contribute to the long standing goal of producing robot controllers that combine the interpretability and precision of model-based optimization with the robustness that model-free RL- based controllers offer.

Understanding the gap between simulation and reality is critical for reinforcement learning with legged robots, which are largely trained in simulation. However, recent work has resulted in sometimes conflicting conclusions with regard to which factors are important for success, including the role of dynamics randomization. In this paper, we aim to provide clarity and understanding on the role of dynamics randomization in learning robust locomotion policies for the Laikago quadruped robot. Surprisingly, in contrast to prior work with the same robot model, we find that direct sim-to-real transfer is possible without dynamics randomization or on-robot adaptation schemes. We conduct extensive ablation studies in a sim-to-sim setting to understand the key issues underlying successful policy transfer, including other design decisions that can impact policy robustness. We further ground our conclusions via sim-to-real experiments with various gaits, speeds, and stepping frequencies. Additional Details: pair.toronto.edu/understanding-dr/

Abstract Humans are highly adept at walking in environments with foot placement constraints, including stepping‐stone scenarios where footstep locations are fully constrained. Finding good solutions to stepping‐stone locomotion is a longstanding and fundamental challenge for animation and robotics. We present fully learned solutions to this difficult problem using reinforcement learning. We demonstrate the importance of a curriculum for efficient learning and evaluate four possible curriculum choices compared to a non‐curriculum baseline. Results are presented for a simulated humanoid, a realistic bipedal robot simulation and a monster character, in each case producing robust, plausible motions for challenging stepping stone sequences and terrains.

Human and animal gaits are often symmetric in nature, which points to the use of motion symmetry as a potentially useful source of structure that can be exploited for learning. By encouraging symmetric motion, the learning may be faster, converge to more efficient solutions, and be more aesthetically pleasing. We describe, compare, and evaluate four practical methods for encouraging motion symmetry. These are implemented via particular choices of structure for the policy network, data duplication, or via the loss function. We experimentally evaluate the methods in terms of learning performance and achieved symmetry, and provide summary guidelines for the choice of symmetry method. We further describe some practical and conceptual issues that arise. Because similar implementation choices exist for other types of inductive biases, the insights gained may also be relevant to other learning problems with applicable symmetry abstractions.

Bipedal locomotion skills are challenging to develop. Control strategies often use local linearization of the dynamics in conjunction with reduced-order abstractions to yield tractable solutions. In these model-based control strategies, the controller is often not fully aware of many details, including torque limits, joint limits, and other non-linearities that are necessarily excluded from the control computations for simplicity. Deep reinforcement learning (DRL) offers a promising model-free approach for controlling bipedal locomotion which can more fully exploit the dynamics. However, current results in the machine learning literature are often based on ad-hoc simulation models that are not based on corresponding hardware. Thus it remains unclear how well DRL will succeed on realizable bipedal robots. In this paper, we demonstrate the effectiveness of DRL using a realistic model of Cassie, a bipedal robot. By formulating a feedback control problem as finding the optimal policy for a Markov Decision Process, we are able to learn robust walking controllers that imitate a reference motion with DRL. Controllers for different walking speeds are learned by imitating simple time-scaled versions of the original reference motion. Controller robustness is demonstrated through several challenging tests, including sensory delay, walking blindly on irregular terrain and unexpected pushes at the pelvis. We also show we can interpolate between individual policies and that robustness can be improved with an interpolated policy.

Differential dynamic programming (DDP) is a widely used trajectory optimization technique that addresses nonlinear optimal control problems, and can readily handle nonlinear cost functions. However, it does not handle either state or control constraints. This paper presents a novel formulation of DDP that is able to accommodate arbitrary nonlinear inequality constraints on both state and control. The main insight in standard DDP is that a quadratic approximation of the value function can be derived using a recursive backward pass, however the recursive formulae are only valid for unconstrained problems. The main technical contribution of the presented method is a derivation of the recursive quadratic approximation formula in the presence of nonlinear constraints, after a set of active constraints has been identified at each point in time. This formula is used in a new Constrained-DDP (CDDP) algorithm that iteratively determines these active set and is guaranteed to converge toward a local minimum. CDDP is demonstrated on several underactuated optimal control problems up to 12D with obstacle avoidance and control constraints and is shown to outperform other methods for accommodating constraints.

Model-based trajectory optimization often fails to find a reference trajectory for under-actuated bipedal robots performing highly-dynamic, contact-rich tasks in the real world due to inaccurate physical models. In this paper, we propose a complete system that automatically designs a reference trajectory that succeeds on tasks in the real world with a very small number of real world experiments. We adopt existing system identification techniques and show that, with appropriate model parameterization and control optimization, an iterative system identification framework can be effective for designing reference trajectories. We focus on a set of tasks that leverage the momentum transfer strategy to rapidly change the whole-body from an initial configuration to a target configuration by generating large accelerations at the center of mass and switching contacts.