Abstract

The use of Internet and Social Media has increased exponentially during the last few years globally giving the opportunity to interact with other people and share ideas, thoughts, opinions etc. Large-scale data are shared every day through social media platforms with enormous speed and reach an incredibly huge number of people. Additionally, the possibility of writing anonymous posts and comments makes it even more easy to express and spread hate speech. Social media platforms, in order to improve the experience of their users, are trying to eliminate comments expressing hatred. In this thesis, we mainly focus on developing automated techniques to identify hate-speech. We start with Traditional techniques used for hate-speech detection, followed by advanced techniques for identifying hate-speech on social media. Lastly we attempt to identify cases where these automated systems can fail miserable and propose technique to make these systems robust. Traditionally, various social media platforms, such as Wikipedia, Facebook, YouTube etc, employ hundreds of staff members as part of their human review team which manually read every reported post and decide if it is inappropriate for the users. Nowadays, having administrators detecting which comments are offensive or relying on user reports are ineffective methods not only due to the large-scale of data produces through social media and also due to the fact that during the last years an increase of hatred is noticed in the modern societies. As of 2018, there are about 317,000 status updates on Facebook every 60 seconds making it harder than finding a needle in a haystack every 60 seconds! We commence our research work with the problem of hate-speech detection on social media. Popular techniques like handcrafted feature-based Machine Learning and rule-based approaches have their own disadvantages. The former method is hard to scale and generalize, while the latter fails to provide good results making it unreliable for use in production level systems. Motivated by the improvements in the computational resources and availability of large annotated datasets, we work towards building deep learning based approaches for hate-speech detection. We propose composite models which utilizes the capability of deep models for generating concise representations along with the power of traditional machine learning classifiers. Every word has at least one meaning when it stands alone. But the meaning can change depending on context, or even over time. A sentence full of neutral words can be hostile (“Only whites should have rights”), and a sentence packed with potentially hostile words (“F**k what, f**k whatever y’all been wearing”) can be neutral when you recognize it as a Kanye West lyric. Motivated by this idea, we then move towards building techniques that utilize the contextual information instead of using just the content for identifying hate-speech. We propose a Context-based neural network architecture that utilizes the relationship between the content & context for identifying hate-speech text. Modeling relationship between the content & the neighboring text (known as context), helps in resolving disambiguity in cases where its very difficult to identify if the text is abusive or not just from the content. Finally we identify issues with the automated hate-speech detection systems and propose novel techniques to build robust models. Use of social-media data for training automated systems poses risk of it learning biases which are abundant on social media. Almost every forum is biased in some form, either women, gender, race, right-wing groups, gay/lesbians, religion etc. Learning powerful systems that can change the user experience requires the system to be fair towards every religion, group or gender. The artificial intelligence can not yet detect/understand these lingual nuances. We propose techniques that identify a type of bias, stereotypical bias, in an arbitrary model and then propose techniques on we can learn unbiased-artificially intelligent systems by observations from the biased social media. We carry out extensive experiments to establish the effectiveness of our methods. We also perform experiments to prove the efficacy of our model on a real-world API, the Perspective API, and show its effectiveness in identifying biased systems.

Abstract

In this thesis, we propose a novel planning technique for monocular camera based Simultaneous Localization and Mapping(VSLAM) and fast Frontier detection method for autonomous explorartion in an indoor evvironment. In VSLAM, the objective is to estimate the trajectory of camera and simultaneously identify key 3D feature points and build a map, using camera as a depth sensor. Unlike a laser range finder(LRF) based SLAM, VSLAM is known to be erroneous when camera motion includes an in-place rotation or feature displacement is large for successive frames. We propose a motion planning framework which combines motion primitives based planning and trajectory optimization approach to generate trajectories which exactly connects an initial and final state and also ensures that the change in camera’s field of view between subsequent instances is less than some specified threshold. As a consequence of this motion planning framework we are able to automate SLAM and generate automated monocular SLAM maps of an indoor lab area. We also show when the robot follows the path of a generic planner, PTAM trajectory breaks more often than when it executes the path computed by the proposed planner. This performance improvement is further utilised to develop an autonomous vision based exploration system. Frontier detection is a critical component in autonomous exploration, wherein the robot decides the next best location to move in order to continue its mapping process. The existing frontier detection methods require dense reconstruction which is difficult to attain in a poorly textured indoor environment using a monocular camera. In this effort, we present an alternate method of detecting frontiers during the course of robot motion that circumvents the requirement of dense mapping. Based on the observation that frontiers typically occur around areas with sudden change in texture (zero-crossings), we propose a novel linear chain Conditional Random Field(CRF) formulation that is able to detect the presence or absence of frontier regions around such areas. We use cues like spread of 3D points and scene change around these areas as an observation to CRF. We demonstrate that this method gives us more relevant frontiers compared to other monocular camera based methods in the literature. Finally, we present results in an indoor environment, wherein frontiers are reliably detected around walls leading to new corridors, doors leading to new rooms or corridors and tables and other objects that open up to a new space in rooms.

Abstract

Sequence Variants are the most common variants observed in human genome, with single nucleotide variations (SNVs) occurring at a frequency of 1 in every 300bp and small insertions and deletions (INDELs) at a slightly lower frequency. When these variations occur in the coding regions, they can have a deleterious effect on the protein product and function, leading to disease situations. Reducing costs of next generation sequencing technologies has made it possible to take genetic profiling to the clinical setting. This requires not just fast and accurate algorithms for variant detection, but also a knowledge-base for variant annotation and prioritization to facilitate tailored therapeutics based on an individual’s genetic profile. With this objective, we have developed a pipeline, Sequence Variants Identification and Annotation (SeqVItA) that provides an end-to-end solution for small sequence variants detection, annotation and prioritization on a single platform. Parallelization of the variant detection step and incorporation of numerous resources to infer functional impact, clinical relevance and drug-variant associations, SeqVItA will benefit the clinical and research communities alike. Its open-source platform and modular framework allows for easy customization of the workflow depending on the data type (single, paired or pooled samples), variant type (germline and somatic), and variant annotation and prioritization. Performance comparison of SeqVItA on simulated data, real genomic data, and detection, interpretation and analysis of somatic variants on 24 liver cancer patients is carried out. In this study we demonstrate the efficacy of annotation module in facilitating personalized medicine based on patient’s mutational landscape.

Abstract

Science journalism is the art of conveying a detailed scientific research paper in a form that non-scientists can understand and appreciate while ensuring that its underlying information is conveyed accurately. It aims to transform jargon-laden scientific articles into a form that a common reader can comprehend while ensuring that the meaning of the article is retained. It plays a crucial role in making scientific content suitable for consumption by the public at large.Recent advances in Deep Learning research and it’s applications in natural language processing have made way to impressive results in Natural Language Generation. We leverage these advances to explore the possibility of their use in journalism, science journalism in particular, as comprehension of scientific content is much harder challenge than most of the other forms of content, like shorthand, which journalists use while writing articles. In this work, we introduce the problem of automated science journalism and present ways to automate some parts of the workflow by automatically generating the ‘title’ of a blog version of a scientific paper. We have built a corpus of 87, 328 pairs of research papers and their corresponding blogs from two science news aggregators and have used it to build Science-Blogger a pipeline based architecture consisting of a two-stage mechanism to generate the blog titles. To demonstrate the models, we built an interactive tool, where a user can give abstract and title of a research paper, which would be processed by our APIs to produce a blog title, along with some relevant information about the model used for the generation. Evaluation using standard metrics indicate viability of the proposed system. Twitter is another social platform where a lot of content of every imaginable category is shared. Naturally, it is also one of the popular media for sharing scientific work apart from blogs. So, we have also experimented with our model to generate tweets, which are roughly of similar length as blog titles. Evaluation on generated tweets also showed promising results. Although significant advances are made in Natural Language Generation, we noticed that evaluation methods didn’t catch up with these advances. Popular metrics like ROUGE and BLEU are based on word overlap. None of these metrics ensure that the generated sentences do not contradict the truth (actual content in the article). It is quite possible that the generated sentences have high overlap with human-written sentences while still contradicting the human-written sentence. Misrepresenting facts is considered a serious problem in journalism. So, a system automating it should explicitly ensure that such misrepresentation and false statements are not generated. Hence, we also formulated a metric to evaluate sentences generated by such automated abstractive natural language generation systems called SSAS: Semantic Similarity for Abstractive Summarization. Ideally a metric evaluating an abstract sys-tem summary should represent the extent to which the system-generated summary approximates the semantic inference conceived by the reader using a human-written reference summary. Most of the previous approaches relied upon word or syntactic sub-sequence overlap to evaluate system-generated summaries. Such metrics cannot evaluate the summary at semantic inference level. Through this work we introduce the metric of Semantic Similarity for Abstractive Summarization (SSAS), which leverages natural language inference and paraphrasing techniques to frame a novel approach to evaluate system summaries at semantic inference level. SSAS is based upon a weighted composition of quantities representing the level of agreement, contradiction, topical neutrality, paraphrasing, and optionally ROUGE score between a system-generated and a human-written summary.

Abstract

Automatic Speech Recognition (ASR) systems have witnessed a lot of progress in the past decade. In high resourced scenarios like English, ASR systems have shown performance compared to human parity level on specific tasks. Speech recognition systems for Indian languages are less studied compared to other high resourced languages like English. India is a developing country with large emerging markets for speech recognition technology. Developing Indian language ASR systems requires certain challenges to addressed which are innate to Indian languages. India is a multilingual society. India has 23 official languages. To penetrate deep into the Indian markets, ASR systems which can be operated in multiple languages are to be developed. Collecting data from a multilingual environment is much tedious task than to acquire data from a monolingual environment. Often Indian language ASR systems have to be developed for low-resourced scenarios. Apart from multilingual nature, bilingualism is very prevalent in the Indian population which leads frequent code-switching and word borrowing between any two languages. Operating parallel ASR systems with code-switching capabilities in Indian scenarios is a huge challenge. This motivated us to work towards multilingual ASR systems which can handle codemixing and word borrowing efficiently. In this thesis, we address various issues related to development of ASR systems for Indian scenarios. An integrated ASR system is developed using common phone-set which can efficiently handle multilingual code-mixed speech. Acoustic modeling approaches such as HMM-GMM, HMM-SGMM and RNN-CTC have been studied to find the most suitable acoustic model. Various acoustic modeling units such as context independent phone, context dependent phone and syllables are explored to find the most suitable unit for developing joint acoustic models. Residual connections have been explored to improve the performance of the joint acoustic models. Studies directed towards supplementing the conventional features along with articulatory features have been explored for developing mulit-lingual ASR systems. Fricative landmarks are detected and the detected landmarks are used as the features for improving the performance of multilingual ASR system. Distinctive features from speech are modeled using a statistical approach and their relevance for improving the performance of a multilingual ASR is explored. In a low resourced scenario when the data is pooled from multiple sources, the meta-level information about the speaker is not accessible. A speaker normalization to handle those scenarios is explored. Some major conclusions from the work are: • Using Common phone-set for training joint acoustic models offers an attractive solution developing ASR systems to handle multilingual and code-mixed scenarios. • Acoustic models that can model context independent phones have performed better compared to the context dependent tri-phone units. RNN-CTC based joint-acoustic model has performed better that HMM-SGMM model. • Using residual networks to develop the joint acoustic models have stabilized the training. They have improved the performance of the acoustic model when the model is sufficiently deep. • Fricative landmarks when fused with the features have improved the performances of the ASR systems when the data size is small, with relatively larges sized datasets the performance have not improved significantly. • Using distinctive features predicted from DNNs along with the input features have not significantly improved the performance of multilingual ASR system. • When the meta-information about the speaker ID is not available, Using the speaker codes derived from a speaker ID network can be used to improve the performance of a multilingual ASR system

Abstract

Empathy allows one to understand distinct cognitive and emotional states of another. Empathy is critical for social interactions and survival. For researchers it is an interesting but challenging proposition to study either in an observer or in the perpetrator of a crime. In the context of rape, observer’s empathic response is required to help the victim overcome the trauma and deliver justice, while lack of empathy in the perpetrator is of interest to understand deviant behavior. Empathy or the lack of it is influenced by perceptions, from self-experiences or those imposed by social stereotypes, and this is in particular evidenced in attitude towards rape victims. The ability to empathize with a rape victim or display the empathy to not commit an aggressive criminal act is based on complex processing of one’s expectations of the physical characteristics, socioeconomic status, and perceptions of credibility and hence deemed to be highly subjective. Each of societal stereotypes requires in-depth study to model expected empathic response or profile deviation. In this thesis we examine a small but critical parameterthat is the rape victim’s appearance and its relation to observer’s empathy. Our hypothesis is loosely based on observations of typical responses post-rape incidence are reported, which is that female victim carrying a non-traditional (as defined by a particular culture- that is, short hair with no bindi/dot on forehead) look, with a darker skin tone and resident of a village evokes lower empathy response in the common citizens. A set of two experiments were designed to understand behavioral (pupillary response) and the neural activations (functional magnetic resonance imaging) associated with empathy networks. In this first study, for stimuli the average female Indian computer-generated faces are photoshopped to reflect a) variation in skin tone/color, b) (non)traditional appearance and c) inclusion of place of residence(urban/rural). Prior to being shown the faces, the participants (20 male graduate students) were informed that the faces were of rape victims. The faces were designed to not show any expression, to reduce bias from facial cues. The results from a preliminary investigation, shown the presence of the motion/empathy network comprising of the insulaanterior cingulate cortex (ACC)-inferior frontal gyrus (IFG) areas to female faces of purported rape victims for all the category of faces, though higher activation in the Insula (area crucial for emotional empathy) was observed for traditional faces compared to non-traditional faces. Similarly, higher activation in empathy network was observed for fair/lighter skin tone faces compared to darker tone faces. No differential activation was found on the basis of place of residence. Interestingly, activations in the perspective or cognitive empathy regions covering the prefrontal cortex were not observed for any condition. In the second experiment, computer-generated faces were photoshopped to reflect lighter to darker skin tones, and pupil size changes as a function of reflected light were correlated to cognitive processes of ‘like’ through rating provided by the participants (70 engineering students). The hypothesis was that reflex reaction to skin tone was partly due to inadequate contrasts especially in darker skin tone before social bias of race is triggered. The results show slight differences in pupil size when perceiving a light tone face or a dark tone face but statistical significance was not found. The average values from the data indicate that people who ‘like’ dark color have smaller pupil size and larger pupil size was noticed in the group that ‘like’ lighter face tones. It is also observed that subjects who marked their self-color as the dark/medium tend to have a preference for the same skin tones in others. The results of the two independent studies provide preliminary evidence for social perceptions of physical appearance and the strength of the techniques (fMRI or eye tracking) to measure empathy and perceptions. Further studies on convicted rapists are required to understand empathy deficiency for rape victims and the underlying reasons for it.

Abstract

Hemiparesis or weakness on one side of the body, due to traumatic brain injury or stroke requires long-term expensive therapy to recover from either mild or severe motor impairment in the upper and lower limbs. Medical research has shown that timely scientific therapy can help regain most of the basic motor movements, while finer motor coordination requires a longer time. The most crucial factor is access to trained therapists and neuro-rehab centers equipped with state-of-the-art assistive systems for upper/lower limb exercises. Physiotherapy exercises can be accessed at dedicated rehabilitation centers or hospitals fitted with expensive clinically tested equipment or with gym equipment modified for specific exercises. Access to clinical rehabilitation therapy for economically poor patients and importantly rural population is sparse in India. They are forced to move to towns or cities with their families for a duration ranging from 3-6 months for therapy sessions disrupting the families and adding to their financial burden. Additionally, the current sessions are unmotivating requiring a doctor or a therapist to constantly monitor their progress. The research presented in this thesis aims to address some of the above-mentioned issues. The systems designed and tested as part of this work focus on regaining basic limb movements for stroke/spinal cord injury patients. The idea originates from integrating games and use of bio-feedback control systems to provide an immersive virtual environment while recording the limb movement progress using wearable or embedded sensors. The analyzed data collected from the gameplay and sensors are remotely accessed by doctors/therapists for monitoring the patient. Three exergame systems i.e. playing games while engaged in physical exercise, were designed, developed and tested on patients. To address joint contracture hemiparesis or increased hypersensitivity in the lower limb extremity, an exergame called Run was designed. A crucial step to regain strength and balance in the lower limbs is the ability to transfer weight from one leg to the other as well as muscle control required to position a foot forward or backward. With these movement requirements, an avatar controlled by the patient is made to run, collect coins and avoid collision with intermittent obstacles. When the avatar collides with an obstacle, he/she needs to perform a particular foot movement exercise to move ahead. The signals to control the gameplay are collected from the sensors positioned to detect the transfer of weight from one lower extremity to another Hypertonia and apraxia (difficulty in arm movement) are two other conditions developed after a stroke. The damage after a stroke leaves muscles and the peripheral nerves incapable of receiving motor signals from the spinal cord. Over time, the muscle tone reduces, and the patient is unable to lift or move the arm. In many cases, the arm and fingers do not respond to external stimulation. Post-stroke, there is an urgency is to recover muscle tone and control with rigorous exercise. Towards this, a game and a sensors circuit were designed, developed and implemented. The game titled Catch, has a simple user graphical interface and requires the patient/player to control a virtual basket to catch apples dropping from a tree. The first step is to swing the arm in an arc of 30-150 degrees over proximity sensors followed by the tactile pressure of the fingers on an object. Embedded pressure sensors were used to collect the applied pressure from the fingers. The signals from the sensors are used to control the game. Motivation is considered a major factor for rehabilitation post stroke. To examine the influence of spirituality and religious experiences in neuro-rehabilitation exercises, a game simulating a famous pilgrim centre was developed. It has also been reported that Post-Stroke Depression (PSD) can impair recovery and religious faith is reported to have a strong positive influence. Hence, the third exergame called Temple Steps was designed and developed. The game had two versions, one with the temple as a theme wherein the participant climbs the stairs to reach the main deity and the second version with trekking as the theme. To test participants motivation stemming from belief, both the versions were used for comparative analysis. The physical interface used was a basic gym stair exercise machine to which sensors and controls for navigation were fitted. Neuropathic pain resulting from conditions such as phantom limb, stroke or chronic regional syndrome Type 1 can be treated with mirror therapy. The last phase of my research was to test the working of Dr. Ramachandrans mirror box on stroke patients. There is no consensus on its working and speculation often lacks the neuroscientific proof. So, a mirror box fitted with cameras, leap motion, and mayo band was developed for measuring the strength of peripheral nervous system signal to the muscle in the aff

Abstract

Turbo codes perform excellently with regard to error correction in physical layer of wireless communication networks. Near Shannon limit bit-error-rate performance of turbo decoders is the key factor that makes it an important aspect of channel decoding. With the surge of expanding wireless communication and very large scale integration (VLSI) industries around the world , it is essential to design a VLSI architecture of flexible data rate channel decoder for targeting the physical layer of next generation 5G standards. With the Moore’s law approaching towards the steady state, it is high-time for the researchers to work on new architectures to enhance the performance for any application, rather relying on CMOS technology scaling. Hence, this motivates us to carry out this work on VLSI architectures for channel decoders. We propose flexible-architecture for soft-input soft-output (SISO) decoder with radix-2/4/8 modes to support multiple data-rates. This work presents designs of major internal blocks of SISO decoder using extensive steering logic to support multiple radix operating-modes. These architectures enable efficient clock-gating of our decoder for low-power consumption in different operating modes. Subsequently, we have aggregated eight SISO decoders with quadratic-permutation polynomial (QPP) interleavers/de- interleavers to design parallel turbo decoder architecture which can operate in multi-radix mode. Suggested SISO decoder is application-specific integrated-circuit (ASIC) synthesized and post layout simulated in UMC 65 nm-CMOS process. Performance analyses in additive-white Gaussian-noise (AWGN) channel environment showed that the bit error rate (BER) of 10 -4 could be achieved at 5 dB and 0.8 dB for SISO and turbo decoders respectively. Implementation result shows that the suggested SISO decoder could achieve throughput in the range 270-810 Mbps with the corresponding power consumption range of 12.24-37.67 mW. In comparison to the state-of-the-art, our design achieved 38% higher throughput and 61% lower power consumption. Similarly, our multi-radix parallel-turbo decoder is hardware prototyped in 28 nm-CMOS Zynq-FPGA board. It delivers a range of data-rates from 160 to 515 Mbps operating at 160 MHz of clock frequency for 8 iterations.

Abstract

Field Programmable Gate Array (FPGA) is gaining popularity in robotics applications due to low cost, portability, low power dissipation, high speed and seamless interface to the hardware. On the other hand, robotics algorithms are mostly arithmetic in nature so they can be easily parallelized and implemented on FPGA. Asynchronous FPGAs have gained remarkable research interest over the last decade.FPGA exceeds the computing power of software-based implementations by breaking the paradigm of sequential execution and accomplishing more per clock cycle by enabling hardware level parallelization at an architectural level. Introducing parallel architectures for a computationally intensive algorithm like Rapidly-Exploring Random Trees(RRT) will result in an exploration that is fast, dense and uniform. A rapidly-exploring random tree (RRT) is an algorithm designed to efficiently search non-convex,high-dimensional spaces by randomly building a space-filling tree. The tree is constructed incrementally from samples drawn randomly from the search space and is inherently biased to grow towards large unsearched areas of the problem. But the overall performance of the algorithm comes down due to high computation delay with the increase in the maps size and geometric constraints. One way to improve the performance is by parallelizing RRT. Here parallelizing RRT refers to multiple RRT modules working in parallel to achieve faster exploration of the map. And to accommodate all the data that is coming from multiple modules an architecture is required. So with the aim to minimize computation delay with the increase in maps size and geometric con- straints, we present the FPGA based hybrid architecture that allows multiple RRTs to work together combined with modified K-means sensitive to the geometric and kinematic constraints of the robot for accelerated and uniform exploration of the map. Through a cost function delineated in later sections, FPGA based combinatorial architecture delivers superlative speed-up but consumes very high power while hierarchical architecture delivers relatively lower speed-up with acceptable power consumption levels. The hybrid architecture combines the qualities of both combinatorial and hierarchical architecture. To determine the number of RRT nodes to be allotted to the combinatorial and hierarchical blocks of the hybrid architecture, a cost function, comprised of fundamentally inversely related speed-up and power parameters, is formulated. This maximization of the cost function, with its associated constraints, is then mathematically solved using a modified branch and bound, that leads to the optimal allocation of RRT modules to both blocks. For the initial placement of RRTs, we came up with a software-defined strategy for identification of these starting points using a modified K-Means. Strategized placing of the seeds (starting points) of each RRT module can lead to a more homogeneous and faster exploration as compared to the indiscriminate placement of the same. Further, to validate the empirical working of the architectures in a real-world scenario, a Zynq-SoC based differential drive robotic system was built as a test platform to run the architectures in real time in a complex environment filled with obstacles. It is observed that this hybrid architecture delivers the highest performance-per-watt out of the three architectures for differential, quad-copter and fixed-wing kinematics. The overall system is a hardware-software co-design to achieve real-time, ASIC like performance that delivers accelerated and homogeneous exploration.

Abstract

Field Programmable Gate Array (FPGA) is gaining popularity in robotics applications due to low cost, portability, low power dissipation, high speed and seamless interface to the hardware. On the other hand, robotics algorithms are mostly arithmetic in nature so they can be easily parallelized and imple- mented on FPGA. Asynchronous FPGAs have gained remarkable research interest over the last decade. FPGA exceeds the computing power of software-based implementations by breaking the paradigm of sequential execution and accomplishing more per clock cycle by enabling hardware level parallelization at an architectural level. Introducing parallel architectures for a computationally intensive algorithm like Rapidly-Exploring Random Trees(RRT) will result in an exploration that is fast, dense and uniform.A rapidly-exploring random tree (RRT) is an algorithm designed to efficiently search non-convex, high-dimensional spaces by randomly building a space-filling tree. The tree is constructed incrementally from samples drawn randomly from the search space and is inherently biased to grow towards large unsearched areas of the problem. But the overall performance of the algorithm comes down due to high computation delay with the increase in the maps size and geometric constraints. One way to improve the performance is by parallelizing RRT. Here parallelizing RRT refers to multiple RRT modules working in parallel to achieve faster exploration of the map. And to accommodate all the data that is coming from multiple modules an architecture is required. So with the aim to minimize computation delay with the increase in maps size and geometric constraints, we present the FPGA based hybrid architecture that allows multiple RRTs to work together combined with modified K-means sensitive to the geometric and kinematic constraints of the robot for accelerated and uniform exploration of the map. Through a cost function delineated in later sections, FPGA based combinatorial architecture delivers superlative speed-up but consumes very high power while hierarchical architecture delivers relatively lower speed-up with acceptable power consumption levels. The hybrid architecture combines the qualities of both combinatorial and hierarchical architec-ture.To determine the number of RRT nodes to be allotted to the combinatorial and hierarchical blocksof the hybrid architecture, a cost function, comprised of fundamentally inversely related speed-up and power parameters, is formulated. This maximization of the cost function, with its associated constraints, is then mathematically solved using a modified branch and bound, that leads to the optimal allocation of RRT modules to both blocks. For the initial placement of RRTs, we came up with a software-defined strategy for identification of these starting points using a modified K-Means. Strategized placing of the seeds (starting points) of each RRT module can lead to a more homogeneous and faster exploration as compared to the indiscriminate placement of the same. Further, to validate the empirical working of the architectures in a real-world scenario, a Zynq-SoC based differential drive robotic system was built as a test platform to run the architectures in real time in a complex environment filled with obstacles. It is observed that this hybrid architecture delivers the highest performance-per-watt out of the three architectures for differential, quad-copter and fixed-wing kinematics. The overall system is a hardware-software co-design to achieve real-time, ASIC like performance that delivers accelerated and homogeneous exploration.