In this paper, we explore the space of running gaits for the bipedal robot Cassie. Our first contribution is to present an approach for optimizing gait efficiency across a spectrum of speeds with the aim of enabling extremely high-speed running on hardware. This raises the question of how the resulting gaits compare to human running mechanics, which are known to be highly efficient in comparison to quadrupeds. Our second contribution is to conduct this comparison based on established human biomechanical studies. We find that despite morphological differences between Cassie and humans, key properties of the gaits are highly similar across a wide range of speeds. Finally, our third contribution is to integrate the optimized running gaits into a full controller that satisfies the rules of the real-world task of the 100m dash, including starting and stopping from a standing position. We demonstrate this controller on hardware to establish the Guinness World Record for Fastest 100m by a Bipedal Robot.

Recent work on sim-to-real learning for bipedal locomotion has demonstrated new levels of robustness and agility over a variety of terrains. However, that work, and most prior bipedal locomotion work, have not considered locomotion under a variety of external loads that can significantly influence the overall system dynamics. In many applications, robots will need to maintain robust locomotion under a wide range of potential dynamic loads, such as pulling a cart or carrying a large container of sloshing liquid, ideally without requiring additional load-sensing capabilities. In this work, we explore the capabilities of reinforcement learning (RL) and sim-to-real transfer for bipedal locomotion under dynamic loads using only proprioceptive feedback. We show that prior RL policies trained for unloaded locomotion fail for some loads and that simply training in the context of loads is enough to result in successful and improved policies. We also compare training specialized policies for each load versus a single policy for all considered loads and analyze how the resulting gaits change to accommodate different loads. Finally, we demonstrate sim-to-real transfer, which is successful but shows a wider sim-to-real gap than prior unloaded work, which points to interesting future research.

Recently, work on reinforcement learning (RL) for bipedal robots has successfully learned controllers for a variety of dynamic gaits with robust sim-to-real demonstrations. In order to maintain balance, the learned controllers have full freedom of where to place the feet, resulting in highly robust gaits. In the real world however, the environment will often impose constraints on the feasible footstep locations, typically identified by perception systems. Unfortunately, most demonstrated RL controllers on bipedal robots do not allow for specifying and responding to such constraints. This missing control interface greatly limits the real-world application of current RL controllers. In this paper, we aim to maintain the robust and dynamic nature of learned gaits while also respecting footstep constraints imposed externally. We develop an RL formulation for training dynamic gait controllers that can respond to specified touchdown locations. We then successfully demonstrate simulation and sim-to-real performance on the bipedal robot Cassie. In addition, we use supervised learning to induce a transition model for accurately predicting the next touchdown locations that the controller can achieve given the robot's proprioceptive observations. This model paves the way for integrating the learned controller into a full-order robot locomotion planner that robustly satisfies both balance and environmental constraints.

The complex dynamics of agile robotic legged locomotion requires motion planning to intelligently adjust footstep locations. Often, bipedal footstep and motion planning use mathematically simple models such as the linear inverted pendulum, instead of dynamically-rich models that do not have closed-form solutions. We propose a real-time optimization method to plan for dynamical models that do not have closed form solutions and experience irrecoverable failure. Our method uses a data-driven approximation of the step-to-step dynamics and of a failure margin function. This failure margin function is an oriented distance function in state-action space where it describes the signed distance to success or failure. The motion planning problem is formed as a nonlinear program with constraints that enforce the approximated forward dynamics and the validity of state-action pairs. For illustration, this method is applied to create a planner for an actuated spring-loaded inverted pendulum model. In an ablation study, the failure margin constraints decreased the number of invalid solutions by between 24 and 47 percentage points across different objectives and horizon lengths. While we demonstrate the method on a canonical model of locomotion, we also discuss how this can be applied to data-driven models and full-order robot models.

Recent work has demonstrated the success of reinforcement learning (RL) for training bipedal locomotion policies for real robots. This prior work, however, has focused on learning joint-coordination controllers based on an objective of following joint trajectories produced by already available controllers. As such, it is difficult to train these approaches to achieve higher-level goals of legged locomotion, such as simply specifying the desired end-effector foot movement or ground reaction forces. In this work, we propose an approach for integrating knowledge of the robot system into RL to allow for learning at the level of task space actions in terms of feet setpoints. In particular, we integrate learning a task space policy with a model-based inverse dynamics controller, which translates task space actions into joint-level controls. With this natural action space for learning locomotion, the approach is more sample efficient and produces desired task space dynamics compared to learning purely joint space actions. We demonstrate the approach in simulation and also show that the learned policies are able to transfer to the real bipedal robot Cassie. This result encourages further research towards incorporating bipedal control techniques into the structure of the learning process to enable dynamic behaviors.

We propose a method to generate actuation plans for a reduced order, dynamic model of bipedal running. This method explicitly enforces robustness to ground uncertainty. The plan generated is not a fixed body trajectory that is aggressively stabilized: instead, the plan interacts with the passive dynamics of the reduced order model to create emergent robustness. The goal is to create plans for legged robots that will be robust to imperfect perception of the environment, and to work with dynamics that are too complex to optimize in real-time. Working within this dynamic model of legged locomotion, we optimize a set of disturbance cases together with the nominal case, all with linked inputs. The input linking is nontrivial due to the hybrid dynamics of the running model but our solution is effective and has analytical gradients. The optimization procedure proposed is significantly slower than a standard trajectory optimization, but results in robust gaits that reject disturbances extremely effectively without any replanning required.

The stochastic nature of renewable energy sources will no doubt place strain upon the electrical distribution networks as power generation is converted to environmentally friendly methods. The use of energy storage technologies could significantly improve the usability of these energy sources. A domestic installation, based on a 4 kWh energy storage unit, is under development and modeling shows that the proposed unit would improve the energy autonomy of a household.

Previous work on the recognition of objects by reasoning about their functionality has not dealt with objects that have moving parts. In this paper we introduce a scenario in which object recognition is accomplished by first deriving an articulated shape model from an observed sequence of 3-D shapes and by then reasoning about the possible functionality of the articulated shape model.