Robot navigation traditionally relies on building an explicit map that is used to plan collision-free trajectories to a desired target. In deformable, complex terrain, using geometric-based approaches can fail to find a path due to mischaracterizing deformable objects as rigid and impassable. Instead, we learn to predict an estimate of traversability of terrain regions and to prefer regions that are easier to navigate (e.g., short grass over small shrubs). Rather than predicting collisions, we instead regress on realized error compared to a canonical system model. We train with an on-policy approach, resulting in successful navigation policies using as little as 50 minutes of training data split across simulation and real world. Our learning-based navigation system is a sample efficient short-term planner that we demonstrate on a Clearpath Husky navigating through a variety of terrain including grassland and forest.

Safe and high-speed navigation is a key enabling capability for real world deployment of robotic systems. A significant limitation of existing approaches is the computational bottleneck associated with explicit mapping and the limited field of view (FOV) of existing sensor technologies. In this paper, we study algorithmic approaches that allow the robot to predict spaces extending beyond the sensor horizon for robust planning at high speeds. We accomplish this using a generative neural network trained from real-world data without requiring human annotated labels. Further, we extend our existing control algorithms to support leveraging the predicted spaces to improve collision-free planning and navigation at high speeds. Our experiments are conducted on a physical robot based on the MIT race car using an RGBD sensor where were able to demonstrate improved performance at 4 m/s compared to a controller not operating on predicted regions of the map.

Efficient exploration through unknown environments remains a challenging problem for robotic systems. In these situations, the robot's ability to reason about its future motion is often severely limited by sensor field of view (FOV). By contrast, biological systems routinely make decisions by taking into consideration what might exist beyond their FOV based on prior experience. We present an approach for predicting occupancy map representations of sensor data for future robot motions using deep neural networks. We develop a custom loss function used to make accurate prediction while emphasizing physical boundaries. We further study extensions to our neural network architecture to account for uncertainty and ambiguity inherent in mapping and exploration. Finally, we demonstrate a combined map prediction and information-theoretic exploration strategy using the variance of the generated hypotheses as the heuristic for efficient exploration of unknown environments.

This paper presents an autonomous perching concept for multirotor aerial vehicles. The Autonomous Grasping Robotic Aerial System for Perching (AGRASP)represents a novel integration of robotics perception, vision-based path planning, and biomimetically-inspired manipulation on a small, lightweight aerial robot with highly-constrained sensor and processing capacity. Computationally lightweight perception algorithms pull candidate perch structures out of a complex environment with no a priori knowledge of the operational space. The innovative manipulator design combines both active grasp and passive grip enabling it to maintain hold on the perch even with all power off. We experimentally demonstrate, for the first time, a quadrotor autonomously detecting and landing on a perch relying solely on onboard sensing and processing.

This paper presents a method for closed-loop propulsion of a screw-type magnetic capsule with embedded Hall-effect sensors using a single rotating actuator magnet. The method estimates the six-degree-of-freedom (6-DOF) pose of the capsule while it is synchronously rotating with the applied field. It is intended for application in active capsule endoscopy of the intestines. An extended Kalman filter, which uses a simplified 2-DOF process model restricting the capsule to forward or backward movement and rotation about its principle axis, is used to provide a full 6-DOF estimate of the capsule's pose as the capsule travels through a lumen. The capsule's movement in the applied field is constantly monitored to determine if the capsule is synchronously rotating with the applied field. Based on this information, the rotation speed of the external source is adjusted to prevent a loss in the desired magnetic coupling. We experimentally demonstrate, for the first time, simultaneous localization and closed-loop propulsion of a capsule through a lumen using a single rotating magnet. Prior work assumed the capsule had no net motion during the localization phase, requiring decoupled localization and propulsion. This closed-loop performance results in a three times speed up in completion time, compared to the previous decoupled approach.

A variety of magnetic devices can be manipulated remotely using a single permanent “actuator” magnet positioned in space by a robotic manipulator. This paper describes the spherical-actuator-magnet manipulator (SAMM), which is designed to replace or augment the singularity-prone spherical wrist used by prior permanent-magnet manipulation systems. The SAMM uses three omniwheels to enable holonomic control of the heading of its magnet's dipole and to enable its magnet to be rotated continuously about any axis of rotation. The SAMM performs closed-loop control of its dipole's heading using field measurements obtained from Hall-effect sensors as feedback, combined with modeled dynamics, using an extended Kalman filter. We describe the operation and construction of the SAMM, develop and characterize controllers for the SAMM's spherical magnet, and demonstrate remote actuation of an untethered magnetic device in a lumen using the SAMM.

A variety of magnetic devices can be manipulated remotely using a single permanent “actuator” magnet positioned in space by a robotic manipulator. This paper presents the spherical-actuator-magnet manipulator (SAMM), which is designed to replace or augment the singularity-prone spherical wrist used by prior permanent-magnet manipulation systems. The SAMM uses three omniwheels to enable holonomic control of a spherical magnet's heading and enable the magnet's instantaneous axis-of-rotation to be set arbitrarily. The SAMM performs closed-loop control of its dipole using field measurements obtained from Hall-effect sensors. We describe the operation and construction of the SAMM, develop and characterize a controller for the SAMM's spherical magnet, and demonstrate remote actuation of an untethered magnetic device in a lumen.

Previous research on the localization of wireless capsule endoscopes with magnetic fields and sensors has typically utilized incremental methods. This paper provides a non-iterative solution to determine the six degree-of-freedom (6-DOF) position and orientation of a wireless capsule endoscope being actuated by a rotating magnetic dipole. Non-iterative solutions in the past have only been used to locate immobile objects. We experimentally demonstrate that our algorithm calculates the 6-DOF position and orientation of capsules that are truly stationary as well as those that are operated in the “step-out” regime, where the magnetic field is rotated too quickly for the capsule to rotate synchronously, but the capsule does undergo chaotic movement.