Agency: Department of Defense | Branch: Defense Advanced Research Projects Agency | Program: SBIR | Phase: Phase II | Award Amount: 1.75M | Year: 2013
The development of actuators for the next generation of robots must not only address the engineering obstacles of power density and efficiency packaged into a lightweight form factor; they must surmount these obstacles using technology that is affordable for commercial users. To meet and exceed these challenges Vecna Robotics proposes the Bundle of McKibbens Actuators (BoMA), a novel approach that relies on groups of hydraulically-powered McKibbens bladder actuators to provide robots with continuous variable force output using highly power-dense and efficient robot muscles at the cost of only cents per actuator. For this Phase II project, Vecna will improve upon the Phase I static models for force-length relations to account for dynamic conditions and provide biomimetic, agonist/antagonist control for adjustable passive and active compliance using multiple actuators as a variable transmission; investigate new materials for each BoMA muscle fiber design to optimize performance and overall system robustness; evaluate valving approaches; and validate the models and their performance in real and simulated testbeds.
Agency: Department of Defense | Branch: Navy | Program: SBIR | Phase: Phase I | Award Amount: 150.00K | Year: 2012
Human operators must closely monitor video for simultaneous situational awareness and threat assessment. For instance, urban environments in a state of constant activity generate numerous visual cues, each of which must be examined so that potential security breaches do not go unnoticed. The need for constant vigilance places a significant burden on the human operator, invariably leading to fatigue and lapses in attention span. Vecna Robotics proposes a video event detection software tool, known as AESOP, that automatically detects time critical events in real-time. AESOP learns new events using a programming by example. With this technique, the analyst teaches the software tool new events by demonstrating actions on concrete examples. Once trained, AESOP processes incoming video and proactively identifies user-defined events in real-time while also indexing the video to simplify forensic analysis. Using state-of-the-art computer vision algorithms, the system identifies and tracks all targets in the scene. Characteristic features for each target are extracted over time yielding feature trajectories which are then efficiently matched to the trained event trajectories. An easy-to-use user interface allows the analyst to visualize and confirm detected events quickly. Furthermore, AESOP"s accuracy can improve by incorporating the confirmed detected events into the training set.
Agency: Department of Defense | Branch: Defense Advanced Research Projects Agency | Program: SBIR | Phase: Phase II | Award Amount: 721.66K | Year: 2012
This Phase II project will extend prototypes and algorithms developed in Phase I for software-based modules for multi-modal command and control of robots using the various sensors and camera hardware on modern handheld devices, i.e. smartphones. Phase I work saw the successful development of new gesture and speech-based control interfaces for driving, manipulation, and surveillance. Phase II work will see the inclusion of advanced artificial intelligence algorithms for task-level supervised autonomy (and the appropriate interface approaches) into these control modules.
Agency: Department of Defense | Branch: Navy | Program: SBIR | Phase: Phase II | Award Amount: 1.00M | Year: 2012
A pneumatic hammer chisel end effector will be developed that uses a simple yet novel fluid routing system. The lightweight device is easily attached to existing MTRS arms and can generate the impact forces required to fracture concrete and packed soil. The end effector requires no modification to the operator control unit and only two connections to the MTRS: a mechanical interface to hold the tool and a pneumatic air supply which is carried on the MTRS chassis. Vibrations are damped using passive mechanical components to absorb energy that would otherwise be transmitted to the MTRS. The goal of the proposed effort is the optimization and fabrication of the innovative shuttling technology and the creation of a complete tool system. This work will include subsystem proof-of-concept testing using hardware that can be adjusted and optimized, and a series of increasingly complete versions, culminating in a fully production ready set of hardware. The option period will expand upon the results of Phase II testing and manufacture a small production batch of hammer chisel end effectors that will be used for extensive user training and testing. These versions will be TRL7 and ready for large scale production, enabling commercialization of the device.
Agency: Department of Defense | Branch: Defense Health Program | Program: SBIR | Phase: Phase I | Award Amount: 150.00K | Year: 2015
Large medical centers can overwhelm patients - for example, Walter Reed National Military Medical Center covers over 2.4 million square feet of clinical space - yet the primary objective for these facilities is to provide patient satisfaction with the healthcare services. A Virtual Concierge application is being proposed to help guide the patients throughout their entire visit at the medical facility. The proposed effort will provide an Application Program Interface (API) platform to interact with the DoD scheduling system, along with a Virtual Concierge mobile app to utilize the appointment information to provide a customized itinerary for the patient. Interfaces will also be established to interact with commercially available technologies that can support Virtual Concierge services, such as digital signage, indoor positioning, and service robots. The Convenient Care Model will be used for designing and developing the application to achieve meaningful and sustainable success.