Legged humanoid robots promise revolutionary mobility and effectiveness in environments built for humans. However, inefficient use of energy significantly limits their practical adoption. The humanoid biped walking anthropomorphic novelly-driven efficient robot for emergency response (WANDERER) achieves versatile, efficient mobility, and high endurance via novel drive-trains and passive joint mechanisms. Results of a test in which WANDERER walked for more than 4 h and covered 2.8 km on a treadmill, are presented. Results of laboratory experiments showing even more efficient walking are also presented and analyzed in this article. WANDERER's energetic performance and endurance are believed to exceed the prior literature in human-scale humanoid robots. This article describes WANDERER, the analytical methods and innovations that enable its design, and system-level energy efficiency results.

In this paper we describe the Open Vision Computer (OVC) which was designed to support high speed, vision guided autonomous drone flight. In particular our aim was to develop a system that would be suitable for relatively small-scale flying platforms where size, weight, power consumption and computational performance were all important considerations. This manuscript describes the primary features of our OVC system and explains how they are used to support fully autonomous indoor and outdoor exploration and navigation operations on our Falcon 250 quadrotor platform.

In this paper we introduce STEPPR (Sandia Transmission-Efficient Prototype Promoting Research), a bipedal robot designed to explore efficient bipedal walking. The initial iteration of this robot achieves efficient motions through powerful electromagnetic actuators and highly back-drivable synthetic rope transmissions. We show how the addition of parallel elastic elements at select joints is predicted to provide substantial energetic benefits: reducing cost of transport by 30 to 50 percent. Two joints in particular, hip roll and ankle pitch, reduce dissipated power over three very different gait types: human walking, human-like robot walking, and crouched robot walking. Joint springs based on this analysis are tested and validated experimentally. Finally, this paper concludes with the design of two unique parallel spring mechanisms to be added to the current STEPPR robot in order to provide improved locomotive efficiency.

The widespread deployment of wireless networks presents an opportunity for localization and mapping using only signal-strength measurements. The current state of the art is to use Gaussian process latent variable models (GP-LVM). This method works well, but relies on a signature uniqueness assumption which limits its applicability to only signal-rich environments. Moreover, it does not scale computationally to large sets of data, requiring O (N3) operations per iteration. We present a GraphSLAM-like algorithm for signal strength SLAM. Our algorithm shares many of the benefits of Gaussian processes, yet is viable for a broader range of environments since it makes no signature uniqueness assumptions. It is also more tractable to larger map sizes, requiring O (N2) operations per iteration. We compare our algorithm to a laser-SLAM ground truth, showing it produces excellent results in practice.

We present the design of a new low-cost series elastic robotic arm. The arm is unique in that it achieves reasonable performance for the envisioned tasks (backlash-free, sub-3mm repeatability, moves at 1.5m/s, 2kg payload) but with a significantly lower parts cost than comparable manipulators. The paper explores the design decisions and tradeoffs made in achieving this combination of price and performance. A new, human-safe design is also described: the arm uses stepper motors with a series-elastic transmission for the proximal four degrees of freedom (DOF), and non-series-elastic robotics servos for the distal three DOF. Tradeoffs of the design are discussed, especially in the areas of human safety and control bandwidth. The arm is used to demonstrate pancake cooking (pouring batter, flipping pancakes), using the intrinsic compliance of the arm to aid in interaction with objects.

We present a series of experiments which explore the use of consumer-grade accelerometers as joint position sensors for robotic manipulators. We show that 6- and 7-dof joint angle estimation is possible by using one 3-d accelerometer for each pair of joints. We demonstrate two calibration approaches and experimental results using accelerometer-based control in both position-control and torque-control regimes. We present a manipulator design combining accelerometer-based sensing with low-cost actuation, and conclude by demonstrating the utility of consumer-grade accelerometers even on high-precision manipulators.

The interpretation of uncertain sensor streams for localization is usually considered in the context of a robot. Increasingly, however, portable consumer electronic devices, such as smartphones, are equipped with sensors including WiFi radios, cameras, and inertial measurement units (IMUs). Many tasks typically associated with robots, such as localization, would be valuable to perform on such devices. In this paper, we present an approach for indoor localization exclusively using the low-cost sensors typically found on smartphones. Environment modification is not needed. We rigorously evaluate our method using ground truth acquired using a laser range scanner. Our evaluation includes overall accuracy and a comparison of the contribution of individual sensors. We find experimentally that fusion of multiple sensor modalities is necessary for optimal performance and demonstrate sub-meter localization accuracy.

We consider the task of grasping novel objects and cleaning fairly cluttered tables with many novel objects. Recent successful approaches employ machine learning algorithms to identify points on the scene that the robot should grasp. In this paper, we show that the task can be significantly simplified by using segmentation, especially with depth information. A supervised localization method is employed to select graspable segments. We also propose a shape completion and grasp planner method which takes partial 3D information and plans the most stable grasping strategy. Extensive experiments on our robot demonstrate the effectiveness of our approach.

High-resolution 3D scanning can improve the performance of object detection and door opening, two tasks critical to the operation of mobile manipulators in cluttered homes and workplaces. We discuss how high-resolution depth information can be combined with visual imagery to improve the performance of object detection beyond what is (currently) achievable with 2D images alone, and we present door-opening and inventory-taking experiments.

In the model-based policy search approach to reinforcement learning (RL), policies are found using a model (or "simulator") of the Markov decision process. However, for high-dimensional continuous-state tasks, it can be extremely difficult to build an accurate model, and thus often the algorithm returns a policy that works in simulation but not in real-life. The other extreme, model-free RL, tends to require infeasibly large numbers of real-life trials. In this paper, we present a hybrid algorithm that requires only an approximate model, and only a small number of real-life trials. The key idea is to successively "ground" the policy evaluations using real-life trials, but to rely on the approximate model to suggest local changes. Our theoretical results show that this algorithm achieves near-optimal performance in the real system, even when the model is only approximate. Empirical results also demonstrate that---when given only a crude model and a small number of real-life trials---our algorithm can obtain near-optimal performance in the real system.

Autonomous helicopter flight is widely regarded to be a highly challenging control problem. This paper presents the first successful autonomous completion on a real RC helicopter of the following four aerobatic maneuvers: forward flip and sideways roll at low speed, tail-in funnel, and nose-in funnel. Our experimental results significantly extend the state of the art in autonomous helicopter flight. We used the following approach: First we had a pilot fly the helicopter to help us find a helicopter dynamics model and a reward (cost) function. Then we used a reinforcement learning (optimal control) algorithm to find a controller that is optimized for the resulting model and reward function. More specifically, we used differential dynamic programming (DDP), an extension of the linear quadratic regulator (LQR).

Target acquisition and continuous surveillance using fixed-wing UAVs is a difficult task due to the many degrees of freedom inherent in aircraft and gimbaled cameras. Mini-UAVs further complicate the problem by introducing severe restrictions on the size and weight of electro-optical sensor assemblies. We present a field-tested mini-UAV gimbal mechanism and flightpath generation algorithm as well as a human-UAV interaction scheme in which the operator manually flies the UAV to produce an estimate of the target position, then allows the aircraft to fly itself and control the gimbal while the operator re fines or moves the target position as required.

We discuss several techniques that assist in the field deployments of fixed-wing mini-UAVs to assist search teams, focusing on automatic takeoff and landing. We also present a real-time flightpath generation routine that performs a spiral search centered on a target point, and a path planner that creates waypoints for searches up mountain canyons.

In some environments, a learning agent must learn to balance competing objectives. For example, a Q-learner agent may need to learn which choices expose the agent to risk and which choices lead to a goal. In this paper, we present a variant of Q-learning that learns a pair of utilities for worlds with dichotomous attributes and show that this algorithm properly balances the competing objectives and, as a result, efficiently identifies satisficing solutions. This occurs because exploration of the environment is restricted to those options which, according to current knowledge, are likely to avoid unjustifiable exposure to risk. We empirically validate the algorithm by (a) showing that the algorithm quickly converges to good policies in several simulated worlds of various complexities and (b) applying the algorithm to learning a force feedback profile for a gas pedal that helps drivers avoid risky situations.

We present several human-UAV interfaces that support real-time control of a small semi-autonomous UAV. These interfaces are designed for searching tasks and other missions that typically do not have a precise predetermined flight plan. We present a detailed analysis of a PDA-based interface and describe how our other interfaces relate to this analysis. We then offer quantative and qualitative performance comparisons of the interfaces, as well as an analysis of their possible real-world applications.