MSR Thesis Defense
MSR Thesis Talk: Gaoyue Zhou
Title: On Generalization and Benchmarking on Physical Robots Abstract: Robotics research has seen significant advancements; however, the field remains predominantly demo-driven, making direct comparisons between methods difficult without replicating them on individual setups. While many simulation benchmarks exist, they usually feature contrived datasets and do not accurately reflect real-world performance. In my thesis, we [...]
MSR Thesis Talk: Heng Yu
Title: Towards Real-time Controllable Neural Face Avatars Abstract: Neural Radiance Fields (NeRF) are compelling techniques for modeling dynamic 3D scenes from 2D image collections. These volumetric representations would be well suited for synthesizing novel facial expressions but for three problems. First, deformable NeRFs are object agnostic and model holistic movement of the scene: they can [...]
MSR Thesis Talk: Winnie Kuang
Title: Design and Integration of Semantic Mapping System for Forest Fire Mitigation Abstract: Remote sensing technologies can provide an automated approach to monitor and analyze conditions in the forest environment over a period of time for forest maintenance and wildfire mitigation efforts. In particular, unmanned aerial vehicles (UAVs) are a promising remote sensing modality since they [...]
MSR Thesis Talk: Jinqi Luo
Title: Vision Model Diagnosis: A Generative Perspective Abstract: In the evolving landscape of computer vision, deep learning has emerged as a transformative force, enhancing a myriad of societal facets. The real-world deployment of such a deep vision model requires a reliable evaluation, particularly when the model can have different sensitivities across various semantic attributes and concepts. [...]
MSR Thesis Talk: Daphne Chen
Title: Learning Task Preferences from Real-World Data Abstract: In order to provide personalized assistance that is capable of adapting to the needs of unique individuals, it is necessary to understand peoples’ preferences for different tasks. Robot assistance often assumes a static model of the individual, while in the real world, people have different capabilities and needs [...]
MSR Thesis Talk: Prasanna Kettavarapalyam Sriganesh
Title: Fast Staircase Detection and Estimation with Multi-View Merging for Multi-Robot Systems Abstract: When robotic systems are deployed in the real world, they demand advanced mobility capabilities to operate in complex, three-dimensional environments designed for human use, e.g., multi-level buildings. Staircases have been an integral part of facilitating vertical movement in these three-dimensional environments. This work [...]
MSR Thesis Talk: Aarush Gupta
Title: LightSpeed: Light and Fast Neural Light Fields on Mobile Devices Abstract: Real-time novel-view image synthesis on mobile devices is prohibitive due to limited on-device computational power and storage. Using volumetric rendering methods, such as NeRF and its derivatives, on mobile devices is not suitable due to the high computational cost of volumetric rendering. On the [...]
MSR Thesis Talk: Akshaya Kesarimangalam Srinivasan
Title: Multi-agent Multi-objective Ergodic Search Abstract: In order to find points of interest in a given domain, many planners use a priori information to guide the search to expedite the detection of targets. We present an approach to direct multiple agents (MA) to search a given domain subject to multiple objectives (MO), each characterized by its own information [...]
MSR Thesis Talk: Joshua Spisak
Title: Stochastic Optimization for Autonomous Navigation, Leveraging Parallel Computation Abstract: Stochastic Optimal Control (SOC) is a framework that allows disturbances and uncertainty in system models to be accounted for in its optimization framework. Despite accounting for this uncertainty, many first and second order methods for solving SOC problems are subject to local minima and are [...]
MSR Thesis Talk: Xuxin Cheng
Title: Learning Legged Robot Agility: Sim-to-Real and Beyond Abstract: Legged robotics has seen significant advancements in both manipulation and locomotion. However, there remain significant gaps compared to their biological counterparts, particularly in energy efficiency, natural motion, and the capacity for agile skills. This thesis primarily focuses on two aspects: the unified control of legged manipulators [...]
MSR Thesis Talk: Nishant Mohanty
Title: Multi-Robot Control using Control Barrier Functions: Theory and Application Abstract: Control Barrier Functions (CBFs) have emerged as a powerful theoretical tool for designing controllers with provable safety guarantees. This work presents a novel methodology that leverages CBFs to synthesize controllers for multi-robot coordination. Two multi-agent use cases are explored, i.e., a) Non-Cooperative Herding and [...]
MSR Thesis Talk: Yuyao Shi
Title: A Learning Approach to Understand How Spinal Cord Learns Multiple Behaviors Abstract: The spinal cord plays a crucial role in the control of human locomotion, generating motor patterns and coordinating reflex responses to sensory signals. Although this spinal control is traditionally viewed as a simple relay system, more recent neurophysiological evidence points to a [...]
Carnegie Mellon University
MSR Thesis Talk: FNU Abhimanyu
Title: Improving Robotic Ultrasound AI Using Optical Flow Abstract: Ultrasound is an important modality for medical intervention such as vascular access because it is safe, portable, and low-cost. However, ultrasound scanning requires trained sonographers who are scarce, and it can be challenging to perform ultrasound examinations in disaster or battlefield scenarios. This motivates us to automate [...]
MSR Thesis Talk: Lucas Casanova De Oliveira Nogueira
Title: SuperLoop: a LIDAR-based SLAM Back-end for Underground Exploration Abstract: Robots deployed in underground scenarios require a SLAM system that can handle a variety of challenges, such as the absence of GPS, large scale maps, bad illumination, and geometrically degenerate environments. It is nearly impossible for any SLAM solution to handle all these challenges perfectly, specially [...]
MSR Thesis Talk: Neil Khera
Title: PyCubed-Mini: A Low-Cost, Open-Source Satellite Research Platform Abstract: Satellite development has become more accessible with decreasing launch costs and shrinking hardware. However, the expenses associated with pre-built satellite kits remain high, making it difficult for student and hobbyist teams to participate. The lack of standardized satellite hardware and software further adds to the challenge, [...]
Strategy assessment for solving rich physical problems
Abstract: We present a framework that acts as an "intuitive physics reasoner" which takes in strategies expressed in natural language (whether from a human or LLM), and assesses their validity based on a physics knowledge library. We believe the ability to quickly determine whether a strategy is worth considering and allocating further resources to planning [...]
MSR Thesis Talk: Siva Kailas
Title: Multi-Robot Information Gathering for Spatiotemporal Environment Modelling Abstract: Learning to predict or forecast spatiotemporal (ST) environmental processes from a sparse set of samples collected autonomously is a difficult task from both a sampling perspective (collecting the best sparse samples) and from a learning perspective (predicting unseen locations or forecasting the next timestep). We investigate [...]
MRS Thesis Talk: Ruijie Fu
Title: Towards Mechanical Communication in Multi-Agent Locomotive Systems: Principally Kinematic Robots on a Shared Platform Abstract: Many biological multi-agent systems exhibit a mechanism for information exchange among individuals known as mechanical communication, which leads to the emergence of collective behavior within the group. One such example is the swarming behavior of bacteria, where they form rafts [...]
Architecture and Algorithms for Space-Based Global Wildlife Tracking
Abstract: Accurate satellite based positioning revolutionized several industries over the past two decades from agriculture to transportation. However, conventional GNSS receivers consume significant amounts of energy and are too large for many applications, including wildlife-tracking which is critical for conservation efforts and improving our understanding of the global climate. To address this capability gap, we [...]
Language-Conditioned Object Detection and Manipulation
Abstract: Traditional object detection methods are often confined to predefined object vocabularies, limiting their versatility in real-world scenarios where robots need to understand and execute diverse household tasks. Additionally, the 2D and 3D perception communities have typically pursued separate approaches tailored to their respective domains. In this thesis, we present a language-conditioned object detector with [...]
Exploring Diverse Interaction Types for Human in the Loop Robot Learning
Abstract: Teaching sessions between humans and robots will need to be maximally informative for optimal robot learning and to ease the human’s teaching burden. However, the bulk of prior work considers one or two modalities through which a human can convey information to a robot—namely, kinesthetic demonstrations and preference queries. Moreover, people will teach robots [...]
Building Robot Hands and Teaching Dexterity
Abstract: Our shared dream is to have robot humanoids with hands complete similar tasks that humans do. While there are a few robot hands available today, the popular opinion is that they are difficult to use, expensive, and hard to obtain which precludes their ubiquitous usage. We argue that this is not an inherent problem [...]
New Methods for Satellite Control
Abstract: Since 2003, the number of satellites launched into orbit has grown from 100 per year to over 2000 per year. Over that same timeframe, incredible advances have been made in control systems for terrestrial robotics and autonomy. Despite the increased quantity of satellites in orbit and the advances made in terrestrial control systems, satellite [...]
[MSR Thesis Talk] Development and Testing of a Software Stack for an Autonomous Racing Vehicle
Abstract: Autonomous racing aims to replicate the human racecar driver with software and sensors. As in traditional motorsports, Autonomous Racing Vehicles (ARVs) are pushed to their dynamic limits in multi-agent scenarios at high (>= 100mph) speeds. This Operational Design Domain (ODD) presents unique challenges across the autonomy stack. The Indy Autonomous Challenge (IAC) is an [...]
[MSR Thesis Talk] Kitchen Robot Case Studies: Learning Manipulation Tasks from Human Video Demonstrations
Abstract: The vision of integrating a robot into the kitchen, capable of acting as a chef, remains a sought-after goal in robotics. Current robotic systems, mostly programmed for specific tasks, fall short in versatility and adaptability to a diverse culinary environment. While significant progress has been made in robotic learning, with advancements in behavior cloning, [...]
[MSR Thesis Talk] Neural Implicit Representations for Medical Ultrasound Volumes and 3D Anatomy-specific Reconstructions
Abstract: Most Robotic Ultrasound Systems (RUSs) equipped with ultrasound-interpreting algorithms rely on building 3D reconstructions of the entire scanned region or specific anatomies. These 3D reconstructions are typically created via methods that compound or stack 2D tomographic ultrasound images using known poses of the ultrasound transducer with the latter requiring 2D or 3D segmentation. While fast, this class [...]
[MSR Thesis Talk] Enhancing RHex Robot Performance with Innovative Bioplastic Legs Responsive to Humidity
Abstract: Designing and developing robots that can effectively navigate real-world environments poses a significant challenge. To overcome this, many robotic systems draw inspiration from the adaptive behaviors of animals, which have evolved to thrive in diverse surroundings. Amphibious animals, for instance, seamlessly transition between walking and swimming, optimizing their locomotion efficiency based on environmental cues. [...]
Alignment for Vision-Language Foundation Model
Abstract: Recent advancements in vision-language foundation models, exemplified by GPT4-Vision and DALL-E 3, have significantly transformed both research and practical applications, ranging from professional assistance to content creation. However, aligning them precisely with specific user goals presents a notable challenge. This thesis introduces innovative strategies for improving this alignment. I will first introduce our novel [...]
Improving Kalman Filter-based Multi-Object Tracking in Occlusion and Non-linear Motion
Abstract: Modern methods solve multi-object tracking from two perspectives: motion modeling and appearance matching. As a classic paradigm, motion-based tracking by Kalman filters suffers from complicated motion patterns and the problem becomes more difficult when we only have noisy bounding boxes. To improve Kalman filter-based multi-object tracking in scenarios with complex motion, occlusion, and crossover, [...]
Improving Kalman Filter-based Multi-Object Tracking in Occlusion and Non-linear Motion
Abstract: Modern methods solve multi-object tracking from two perspectives: motion modeling and appearance matching. As a classic paradigm, motion-based tracking by Kalman filters suffers from complicated motion patterns and the problem becomes more difficult when we only have noisy bounding boxes. To improve Kalman filter-based multi-object tracking in scenarios with complex motion, occlusion, and crossover, [...]
[MSR Thesis Talk] SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM
Abstract: Dense simultaneous localization and mapping (SLAM) is crucial for numerous robotic and augmented reality applications. However, current methods are often hampered by the non-volumetric or implicit way they represent a scene. This talk introduces SplaTAM, an approach that leverages explicit volumetric representations, i.e., 3D Gaussians, to enable high-fidelity reconstruction from a single unposed RGB-D [...]
Human Perception of Robot Failure and Explanation During a Pick-and-Place Task
Abstract: In recent years, researchers have extensively used non-verbal gestures, such as head and arm movements, to express the robot's intentions and capabilities to humans. Inspired by past research, we investigated how different explanation modalities can aid human understanding and perception of how robots communicate failures and provide explanations during block pick-and-place tasks. Through an in-person [...]
Learning Distributional Models for Relative Placement
Abstract: Relative placement tasks are an important category of tasks in which one object needs to be placed in a desired pose relative to another object. Previous work has shown success in learning relative placement tasks from just a small number of demonstrations, when using relational reasoning networks with geometric inductive biases. However, such methods fail [...]
Transfer Learning via Temporal Contrastive Learning Inbox
Abstract: This thesis introduces a novel transfer learning framework for deep reinforcement learning. The approach automatically combines goal-conditioned policies with temporal contrastive learning to discover meaningful sub-goals. The approach involves pre-training a goal-conditioned agent, finetuning it on the target domain, and using contrastive learning to construct a planning graph that guides the agent via sub-goals. Experiments [...]
Towards Equitable Representation in Text-to-Image Generation
Abstract: Accurate representation in media is known to improve the well-being of the people who consume it. There is a growing concern about the increasing use of generative AI in media as the generative image models trained on large web-crawled datasets such as LAION are known to produce images with harmful stereotypes and misrepresentations of various groups, [...]
3D Inference from Unposed Sparse View Images
Abstract: We propose UpFusion, a system that can perform novel view synthesis and infer 3D representations for generic objects given a sparse set of reference images without corresponding pose information. Current sparse-view 3D inference methods typically rely on camera poses to geometrically aggregate information from input views, but are not robust in-the-wild when such information [...]
Tightly Coupled LIDAR-Inertial Odometry
Abstract: In the age of self-driving, LIDAR and IMU represent two of the most ubiqui- tous sensors in use. Kalman Filtering and loosely coupled approaches dominate industry techniques, while current research trends towards a more tightly coupled formulation involving a joint optimization of IMU and LIDAR measurements. After two years of experience working with and [...]
In Pursuit of Open-World Mobile Manipulation
Abstract: Deploying robots in open-ended unstructured environments such as homes has been a long-standing research problem. However, robots are often studied only in closed-off lab settings, and prior mobile manipulation work is restricted to pick-move-place, which is arguably just the tip of the iceberg in this area. In this thesis, we introduce the Open-World Mobile [...]
Carnegie Mellon University
Geometric Heuristics Enhance POCUS AI for Pneumothorax
Abstract: The interpretation of Point-of-care ultrasound (POCUS) images poses a challenge due to the scarcity of high-quality labelled data for training AI models in the medical domain. To address this limitation, novel methodologies were developed to train POCUS AI models using limited data, integrating geometric heuristics derived from expert clinicians. Focused on diagnosing pneumothorax, heuristics [...]
Optimal Control and Robot Learning on Agile Safety-Critical Systems
Abstract: We present a pipeline of optimal control methods for learning an optimal control policy and locally accurate dynamics models for agile and safety-critical robots using autonomous racing as an application example. We introduce Spline-Opt, a fast offline/online optimization and planning method that can produce a reasonably good initial optimal trajectory given very little dynamics [...]
Vision Model Diagnosis and Improvement Via Large Pretrained Models
Abstract: As AI becomes increasingly pervasive in real-world applications, the deployment of machine learning models in real-world applications has underscored critical challenges in model robustness, fairness and performance. Despite significant advances, existing models often exhibit biases, fail to generalize across diverse data distributions, and struggle with unexpected input variations, leading to suboptimal or even discrimina- [...]
Indoor Localization and Mapping with 4D mmWave Imaging Radar
Abstract: State estimation is a crucial component for the successful implementation of robotic systems, relying on sensors such as cameras, LiDAR, and IMUs. However, in real-world scenarios, the performance of these sensors is degraded by challenging environments, e.g. adverse weather conditions and low-light scenarios. The emerging 4D imaging radar technology is capable of providing robust perception in adverse conditions. [...]
PIE-FRIDA: Personalized Interactive Emotion-Guided Collaborative Human-Robot Art Creation
Abstract: The introduction of generative AI has brought about many improvements in the artistic world. It allows many individuals to create artwork via simple descriptive text prompts. This has, in particular, created an avenue for non-artistic individuals to express their thoughts through generated art. Our work focuses on how emotion can be added as an [...]
Simulated Encounters of the Third Kind: Scenario-Based Approach to Designing Guide Robots
Abstract: Navigating through unfamiliar environments is a challenging task. For people who are blind or have low vision (BLV), navigation can be particularly daunting. Guide robots are a type of service robot that can assist BLV people with navigation tasks. A significant amount of research related to guide robots has focused on technical contributions, while a [...]
Super Odometry: Selective Fusion Towards All-degraded Environments
Abstract: Robust odometry is at the core of robotics and autonomous systems operating navigation, exploration, and locomotion in complex environments for a broad spectrum of applications. While great progress has been made, the robustness of the odometry system still remains a grand challenge. This talk introduces Super Odometry, an approach that leverages selective fusion to [...]
Learning on the Move: Integrating Action and Perception for Mobile Manipulation
Abstract: While there has been remarkable progress recently in the fields of manipulation and locomotion, mobile manipulation remains a long-standing challenge. Compared to locomotion or static manipulation, a mobile system must make a diverse range of long-horizon tasks feasible in unstructured and dynamic environments. While the applications are broad and interesting, there are a plethora [...]
Continual Personalization of Human Actions with Prompt Tuning
Abstract: In interactive computing devices (VR/XR headsets), users interact with the virtual world using hand gestures and body actions. Typically, models deployed in such XR devices are static and limited to their default set of action classes. The goal of our research is to provide users and developers with the capability to personalize their experience by [...]
Reinforcement Learning with Spatial Reasoning for Dexterous Robotic Manipulation
Abstract: Robotic manipulation in unstructured environments requires adaptability and the ability to handle a wide variety of objects and tasks. This thesis presents novel approaches for learning robotic manipulation skills using reinforcement learning (RL) with spatially-grounded action spaces, addressing the challenges of high-dimensional, continuous action spaces and alleviating the need for extensive training data. Our [...]
Leveraging Vision, Force Sensing, and Language Feedback for Deformable Object Manipulation
Deformable object manipulation represents a significant challenge in robotics due to its complex dynamics, lack of low-dimensional state representations, and severe self-occlusions. This challenge is particularly critical in assistive tasks, where safe and effective manipulation of various deformable materials can significantly improve the quality of life for individuals with disabilities and address the growing needs [...]
CBGT-Net: A Neuromimetic Architecture for Robust Classification of Streaming Data
Abstract: This research introduces CBGT-Net, a neural network model inspired by the cortico-basal ganglia-thalamic (CBGT) circuits in mammalian brains, which are crucial for critical thinking and decision-making. Unlike traditional neural network models that generate an output for each input or after a fixed sequence of inputs, CBGT-Net learns to produce an output once sufficient evidence [...]
Enhancing Robot Perception and Interaction Through Structured Domain Knowledge
Abstract: Despite the advancements in deep learning driven by increased computational power and large datasets, significant challenges remain. These include difficulty in handling novel entities, limited mechanisms for human experts to update knowledge, and lack of interpretability, all of which are crucial for human-centric applications like assistive robotics. To address these issues, we propose leveraging [...]
Towards Universal Place Recognition
Title: Towards Universal Place Recognition Abstract: Place Recognition is essential for achieving robust robot localization. However, current state-of-art systems remain environment/domain-specific and fragile. By leveraging insights from vision foundation models, we present AnyLoc, a universal VPR solution that performs across diverse environments without retraining or fine-tuning, significantly outperforming supervised baselines. We further introduce MultiLoc, and enable [...]
GNSS-denied Ground Vehicle Localization for Off-road Environments with Bird’s-eye-view Synthesis
Abstract: Global localization is essential for the smooth navigation of autonomous vehicles. To obtain accurate vehicle states, on-board localization systems typically rely on Global Navigation Satellite System (GNSS) modules for consistent and reliable global positioning. However, GNSS signals can be obstructed by natural or artificial barriers, leading to temporary system failures and degraded state estimation. On the [...]
Scaling up Robot Skill Learning with Generative Simulation
Abstract: Generalist robots need to learn a wide variety of skills to perform diverse tasks across multiple environments. Current robot training pipelines rely on humans to either provide kinesthetic demonstrations or program simulation environments with manually-designed reward functions for reinforcement learning. Such human involvement is an important bottleneck towards scaling up robot learning across diverse [...]
Simulation as a Tool for Conspicuity Measurement
Abstract: The use of unmanned aerial vehicles (UAVs) for time critical tasks is becoming increasingly popular. Operators are expected to use information from these swarms to make real-time and informed decisions. Consequently, detecting and recognizing targets from video is extremely pivotal to the success of these systems. At greater altitudes or with more vehicles, this [...]
VP4D: View Planning for 3D and 4D Scene Understanding
Abstract: View planning plays a critical role by gathering views that optimize scene reconstruction. Such reconstruction has played an important part in virtual production and computer animation, where a 3D map of the film set and motion capture of actors lead to an immersive experience. Current methods use uncertainty estimation in neural rendering of view [...]
Automating Annotation Pipelines by leveraging Multi-Modal Data
Abstract: The era of vision-language models (VLMs) trained on large web-scale datasets challenges conventional formulations of “open-world" perception. In this work, we revisit the task of few-shot object detection (FSOD) in the context of recent foundational VLMs. First, we point out that zero-shot VLMs such as GroundingDINO significantly outperform state-of-the-art few-shot detectors (48 vs. 33 AP) [...]
Leveraging Affordances for Accelerating Online RL
Abstract: The inability to explore environments efficiently makes online RL sample-inefficient. Most existing works tackle this problem in a setting devoid of prior information. However, additional affordances may often be cheaply available at the time of training. These affordances include small quantities of demo data, simulators that can reset to arbitrary states and domain specific [...]
Safe, Robust and Adaptive Model Learning for Agile Robots: Autonomous Racing
Abstract: In recent years there has been a rapid development in agile robots capable of operating at their limits in dynamic environments. Autonomous racing and recent developments in it also spurred by competitions such as the Indy Autonomous Challenge, A2RL, and F1Tenth have shown how modern autonomous control algorithms are capable of operating racecars at [...]
Improving Lego Assembly with Vibro-Tactile Feedback
Abstract: Robotic manipulation is an important area of research to improve the level of efficiency and autonomy in manufacturing processes. Due to the high precision and repeatability of industrial robot arms, robotic manufacturing tasks are dominated by simple pick, place, and peg insertion actions performed in a highly structured environment. Lego blocks are an excellent [...]