Advancements in deep learning have catalyzed growth in robotic applications, extending their utility beyond constrained settings. Nevertheless, a significant challenge remains in en- abling robots to efficiently navigate and interact within unstructured and dynamic environments. Existing methods in robot navigation require the use of dense geometric representations such as high definition maps or full 3D reconstruction. But these methods are non trivial and consume significant resources in both creation and usage. They also become stale for environments with constant changes. To be able to scale in terms of size and novelty of the environment, new algorithms that use representations accounting for semantics is required. Besides that, to be able to interact and collaborate with humans, these representations need to be able to ground the visual information in other modalities such as text, while retaining a long term memory. This thesis presents work on these directions, development of new approach and the discussion on the experiments applying these methods to navigation and robot instruction following in home environments.

We propose a novel computing approach, called “Race Logic”, which utilizes a new data representation to accelerate a broad class of optimization problems, such as those solved by dynamic programming algorithms. The core idea of Race Logic is to deliberately engineer race conditions in a circuit to perform useful computation. In Race Logic, information, instead of being represented as logic levels (as is done in conventional logic), is represented as a timing delay. Computations can then be performed by observing the relative propagation times of signals injected into a configurable circuit (i.e. the outcome of races through the circuit).

In this dissertation I will introduce Race Based computation and talk about multiple VLSI implementations. We first begin by considering a synchronous approach, which uses simple clocked delay elements. Though this synchronous implementation outperforms highly optimized conventional implementations of the well-studied, DNA sequence alignment problem, its third order energy scaling with problem size and limited dynamic range of timing delays are its major pitfalls. Next, in the search for energy efficiency, we study asynchronous designs in order to understand the performance trade-offs and applicability of this new architecture. Finally, I will present the results of a prototype asynchronous Race Logic chip and demonstrate that Race-Based computations can align up to 10 million 50 symbol long DNA sequences per second, about 2-3 orders of magnitude faster than the state of the art general purpose computing systems.

In resource limited, large scale underwater sensor networks, cooperative communication over multiple hops offers opportunities to save power. Intermediate nodes between source and destination act as cooperative relays. Herein, protocols coupled with space-time block code (STBC) strategies are proposed and analyzed for distributed cooperative communication. Amplify-and-forward type protocols are considered, in which intermediate relays do not attempt to decode the information. The Alamouti-based cooperative scheme proposed by Hua et al (2003) for flat-fading channels is generalized in order work in the presence of multipath, thus addressing a main characteristic of underwater acoustic channels. A time-reversal distributed space-time block code (TR-DSTBC) is proposed, which extends the dual-antenna TR-STBC (time reversal space-time block code) approach from Lindskog and Paulraj (2000) to a cooperative communication scenario for signaling in multipath. It is first shown that, just as in the dual-antenna STBC case, TR along with the orthogonality of the DSTBC essentially allows for decoupling of the vector ISI detection problem into separate scalar problems, and thus yields strong performance (compared with single hop communication) and with substantially reduced complexity over non-orthogonal schemes.

In this work, communication protocols and encoding schemes are analyzed and designed to achieve diversity and superior probability of decoding error for networks of distributed terminals. In particular, a single source and destination pair are considered with a collection of R cooperating relay nodes in between. Communication protocols and encoding schemes based on methods of amplify-and-forward and decode-and-forward coupled with Alamouti based orthogonal space-time block codes and optimum minimum metric space-time block codes are considered. The achievable diversity of a previously proposed amplify-and-forward/Alamouti method is derived and compared to that of a decode-and-forward scheme. For modest SNRs, the decode-and-forward scheme outperforms the amplify-and-forward based scheme. However, poor source-to-relay link quality can severely impact the decode- and-forward scheme and thus a hybrid scheme is proposed and shown to provide superior performance to the previously two discussed schemes.