The biomechanics community has recently made progress toward understanding the role of rapid arm movements in human stability recovery. However, comparatively little work has been done exploring this type of control in humanoid robots. We provide a summary of recent insights into the functional contributions of arm recovery motions in humans and experimentally demonstrate advantages of this behavior on a dynamically stable mobile manipulator. Using Bayesian optimization, the robot efficiently discovers policies that reduce total energy expenditure and recovery footprint, and increase ability to stabilize after large impacts.
We introduce CST, an algorithm for constructing skill trees from demonstration trajectories in continuous reinforcement learning domains. CST uses a changepoint detection method to segment each trajectory into a skill chain by detecting a change of appropriate abstraction, or that a segment is too complex to model as a single skill. The skill chains from each trajectory are then merged to form a skill tree. We demonstrate that CST constructs an appropriate skill tree that can be further refined through learning in a challenging continuous domain, and that it can be used to segment demonstration trajectories on a mobile manipulator into chains of skills where each skill is assigned an appropriate abstraction.
We propose an approach to control learning from demonstration that first segments demonstration trajectories to identify subgoals, then uses model-based con- trol methods to sequentially reach these subgoals to solve the overall task. Using this approach, we show that a mobile robot is able to solve a combined navigation and manipulation task robustly after observing only a single successful trajectory.
We present an initial demonstration of dexterous mobility using the uBot-5, a dynamically balancing mobile manipulator. Dexterous mobility refers generally to a level of bodily resourcefulness that permits the autonomous reassignment of effectors for the purpose of maintaining mobility in a variety of situations. We begin by describing a set of postural stability controllers in terms of a small number of simple control objectives. We then show how the resulting postures support dexterous mobility by enabling a new ldquoknuckle walkingrdquo mobility mode. In a preliminary experiment, we develop this mobility mode by formulating a practical reinforcement learning problem that allows the robot to learn an efficient gait on-line in a single trial.
Ocular dominance (OD) plasticity is a robust paradigm for examining the functional consequences of synaptic plasticity. Previous experimental and theoretical results have shown that OD plasticity can be accounted for by known synaptic plasticity mechanisms, using the assumption that deprivation by lid suture eliminates spatial structure in the deprived channel. Here we show that in the mouse, recovery from monocular lid suture can be obtained by subsequent binocular lid suture but not by dark rearing. This poses a significant challenge to previous theoretical results. We therefore performed simulations with a natural input environment appropriate for mouse visual cortex. In contrast to previous work, we assume that lid suture causes degradation but not elimination of spatial structure, whereas dark rearing produces elimination of spatial structure. We present experimental evidence that supports this assumption, measuring responses through sutured lids in the mouse. The change in assumptions about the input environment is sufficient to account for new experimental observations, while still accounting for previous experimental results.
This article introduces the problem of determining the probability that a rotating and bouncing cylinder (i.e., flipped coin) will land and come to rest on its edge. We present this problem and analysis as a practical, nontrivial example to introduce the reader to Bayesian model comparison. Several models are presented, each of which take into consideration different physical aspects of the problem and the relative effects on the edge landing probability. The Bayesian formulation of model comparison is then used to compare the models and their predictive agreement with data from hand-flipped cylinders of several sizes.
Rate-based neuron models have been successful in understanding many aspects of development such as the development of orientation selectivity(Bienenstock et al., 1982; Oja, 1982; Linsker, 1986; Miller, 1992; Bell and Sejnowski, 1997), the particular dynamics of visual deprivation(Blais et al., 1999) and the development of direction selectivity(Wimbauer et al., 1997; Blais et al., 2000). These models do not address phenomena such as temporal coding, spike-timing dependant synaptic plasticity, or any short-time behavior of neurons. More detailed spiking models (Song et.al, 2000; Shouval et.al. 2002; Yeung et.al. 2004) address these issues, and have had some success, but have failed to develop receptive fields in natural environments. These more detailed models are difficult to explore, given their large number of parameters and the run-time computational limitations. In addition, their results are often difficult to compare directly with the rate-based models. We propose a model, which we call a spiking-rate model, which can serve as a middle-ground between the over simplistic rate-based models, and the more detailed spiking models. The spiking-rate model is a spiking model where all of the underlying processes are continuous Poisson, the summation of inputs is entirely linear (although non-linearities can be added), and the generation of outputs is done by calculating a rate output and then generating an appropriate Poisson spike train. In this way, the limiting behavior is identical to a rate-based model, but the properties of spiking models can be incorporated more easily. We present the development of receptive fields with this model in various visual environments. We then present the necessary conditions for the receptive field development in the spiking-rate models, and make comparisons to detailed spiking models, in order to more clearly understand the necessary conditions for receptive field development.
Differential Dynamic Programming (DDP) has become a popular approach to performing trajectory optimization for complex, underactuated robots. However, DDP presents two practical challenges. First, the evaluation of dynamics derivatives during optimization creates a computational bottleneck, particularly in implementations that capture second-order dynamic effects. Second, constraints on the states (e.g., boundary conditions, collision constraints, etc.) require additional care since the state trajectory is implicitly defined from the inputs and dynamics. This paper addresses both of these problems by building on recent work on Unscented Dynamic Programming (UDP)---which eliminates dynamics derivative computations in DDP---to support general nonlinear state and input constraints using an augmented Lagrangian. The resulting algorithm has the same computational cost as first-order penalty-based DDP variants, but can achieve high-accuracy constraint satisfaction without the numerical ill-conditioning associated with penalty methods. We present results demonstrating its favorable performance on several simulated dynamical systems including a quadrotor and 7-DoF robot arm.
Many critical robotics applications require robustness to disturbances arising from unplanned forces, state uncertainty, and model errors. Motion planning algorithms that explicitly reason about robustness require a coupling of trajectory optimization and feedback design, where the system's closed-loop response to bounded disturbances is optimized. Due to the often-heavy computational demands of solving such problems, the practical application of robust trajectory optimization in robotics has so far been limited. We derive a tractable robust optimization algorithm that combines direct transcription with linear-quadratic control design to reason about closed-loop responses to disturbances. In the case of ellipsoidal disturbance sets, the state and input deviations along a nominal trajectory can be computed locally in closed form, thus allowing for fast evaluations of robust cost and constraint functions. The resulting algorithm, called DIRTREL, is an extension of classical direct transcription that demonstrably improves tracking performance over non-robust formulations while incurring only a modest increase in computational cost. We evaluate the algorithm in several simulated robot control tasks.
A micro aerial vehicle with a variable forward-sweep wing is proposed with the goal of enhancing performance and controllability during high-angle-of-attack perching maneuvers. Data is presented from a series of wind tunnel experiments to quantify the aerodynamic effects of forward sweep over a range of angles of attack from -25 degrees to +75 degrees. A nonlinear dynamics model is constructed using the wind tunnel data to gain further insight into aircraft flight dynamics and controllability. Simulated perching trajectories optimized with a direct collocation method indicate that the forward-swept wing configuration can achieve qualitatively different lower-cost perching maneuvers than the straight wing configuration.
Operating a high degree of freedom mobile manipulator, such as a humanoid, in a field scenario requires constant situational awareness, capable perception modules, and effective mechanisms for interactive motion planning and control. A well-designed operator interface presents the operator with enough context to quickly carry out a mission and the flexibility to handle unforeseen operating scenarios robustly. By contrast, an unintuitive user interface can increase the risk of catastrophic operator error by overwhelming the user with unnecessary information. With these principles in mind, we present the philosophy and design decisions behind Director---the open-source user interface developed by Team MIT to pilot the Atlas robot in the DARPA Robotics Challenge (DRC). At the heart of Director is an integrated task execution system that specifies sequences of actions needed to achieve a substantive task, such as drilling a wall or climbing a staircase. These task sequences, developed a priori, make online queries to automated perception and planning algorithms with outputs that can be reviewed by the operator and executed by our whole-body controller. Our use of Director at the DRC resulted in efficient high-level task operation while being fully competitive with approaches focusing on teleoperation by highly-trained operators. We discuss the primary interface elements that comprise the Director and provide analysis of its successful use at the DRC.
Trajectory optimization algorithms are a core technology behind many modern nonlinear control applications. However, with increasing system complexity, the computation of dynamics derivatives during optimization creates a computational bottleneck, particularly in second-order methods. In this paper, we present a modification of the classical Differential Dynamic Programming (DDP) algorithm that eliminates the computation of dynamics derivatives while maintaining similar convergence properties. Rather than relying on naive finite difference calculations, we propose a deterministic sampling scheme inspired by the Unscented Kalman Filter that propagates a quadratic approximation of the cost-to-go function through the nonlinear dynamics at each time step. Our algorithm takes larger steps than Iterative LQR---a DDP variant that approximates the cost-to-go Hessian using only first derivatives---while maintaining the same computational cost. We present results demonstrating its numerical performance in simulated balancing and aerobatic flight experiments.
Contact constraints, such as those between a foot and the ground or a hand and an object, are inherent in many robotic tasks. These constraints define a manifold of feasible states; while well understood mathematically, they pose numerical challenges to many algorithms for planning and controlling whole-body dynamic motions. In this paper, we present an approach to the synthesis and stabilization of complex trajectories for both fully-actuated and underactuated robots subject to contact constraints. We introduce a trajectory optimization algorithm (DIRCON) that extends the direct collocation method, naturally incorporating manifold constraints to produce a nominal trajectory with third-order integration accuracy–-a critical feature for achieving reliable tracking control. We adapt the classical time-varying linear quadratic regulator to produce a local cost-to-go in the manifold tangent plane. Finally, we descend the cost-to-go using a quadratic program that incorporates unilateral friction and torque constraints. This approach is demonstrated on three complex walking and climbing locomotion examples in simulation.
This paper describes a collection of optimization algorithms for achieving dynamic planning, control, and state estimation for a bipedal robot designed to operate reliably in complex environments. To make challenging locomotion tasks tractable, we describe several novel applications of convex, mixed-integer, and sparse nonlinear optimization to problems ranging from footstep placement to whole-body planning and control. We also present a state estimator formulation that, when combined with our walking controller, permits highly precise execution of extended walking plans over non-flat terrain. We describe our complete system integration and experiments carried out on Atlas, a full-size hydraulic humanoid robot built by Boston Dynamics, Inc.