Student Talks
Carnegie Mellon University
Towards Reconstructing Non-rigidity from Single Camera
Abstract: In this talk we will discuss how to infer 3D from images captured by a single camera, without assuming the target scenes / objects being static. The non-static setting makes our problem ill-posed and challenging to solve, but is vital in practical applications where target-of-interest is non-static. To solve ill-posed problems, the current trend [...]
MSR Thesis Talk: Sarvesh Patil
Title: Soft Delta Robots for Dexterous Manipulation Abstract: Dexterous manipulation capabilities of end-effectors afford us a wide range of strategies for fine-grained manipulation tasks. Recent utilization of readily available materials like soft filaments and silicone elastomers has enabled the development of low-cost mechanically intelligent robotic manipulators. This is important for democratizing robot manipulation and increasing [...]
Large Scale Dense 3D Reconstruction via Sparse Representations
Abstract: Dense 3D scene reconstruction is in high demand today for view synthesis, navigation, and autonomous driving. A practical reconstruction system inputs multi-view scans of the target using RGB-D cameras, LiDARs, or monocular cameras, computes sensor poses, and outputs scene reconstructions. These algorithms are computationally expensive and memory-intensive due to the presence of 3D data. [...]
MSR Thesis Talk: Fan Yang
Title: Exploring Safe Reinforcement Learning for Sequential Decision Making Abstract: Safe Reinforcement Learning (RL) focuses on the problem of training a policy to maximize the reward while ensuring safety. It is an important step towards applying RL to safety-critical real-world applications. However, safe RL is challenging due to the trade-off between the two objectives [...]
Incorporating Robustness into Learning-Based Aircraft Detection and Tracking Systems
Abstract: In the field of aviation, the Detect and Avoid (DAA) problem deals with incorporating collision avoidance capabilities into current autopilot navigation systems. In order to standardize DAA capabilities, ASTM has published performance requirements to define safe DAA operations of unmanned aircraft systems (UAS). However, the performance of DAA models are entirely dependent on the [...]
Carnegie Mellon University
MSR Thesis Talk: Siddarth Venkatraman
Title: Latent Skill Models for Offline Reinforcement Learning Abstract: Offline reinforcement learning (RL) holds promise as a means to learn high-value policies from a static dataset, without the need for further environment interactions. However, a key challenge in offline RL lies in effectively stitching portions of suboptimal trajectories from the static dataset while avoiding extrapolation [...]
Long-Tailed 3D Detection via Multi-Modal Fusion
Abstract: Contemporary autonomous vehicle (AV) benchmarks have advanced techniques for training 3D detectors, particularly on large-scale LiDAR data. Surprisingly, although semantic class labels naturally follow a long-tailed distribution, these benchmarks focus on only a few common classes (e.g., pedestrian and car) and neglect many rare classes in-the-tail (e.g., debris and stroller). However, in the real [...]
MSR Thesis Talk: Eric Schneider
Title: Phenotyping and Skeletonization for Agricultural Robotics Abstract: Scientific phenotyping of plants is a crucial aspect of experimental plant breeding. By accurately measuring plant characteristics, phenotyping plays a vital role in the development of new plant varieties that are better adapted to specific environments and have improved yield, quality, and resistance to stress and disease. In [...]
MSR Thesis Talk: Shivesh Khaitan
Zoom Link: https://cmu.zoom.us/j/95273358670?pwd=Z09Jc3g1aDV1dTdTMEVUWUwxcUZPQT09 Meeting ID: 952 7335 8670 Passcode: 050721 Title: Exploring Reinforcement Learning approaches for Safety Critical EnvironmentsAbstract: Reinforcement Learning (RL) has emerged as a powerful paradigm for addressing challenging decision-making and robotic control tasks. By leveraging the principles of trial-and-error learning, RL algorithms enable agents to learn optimal strategies through interactions with an environment. However, [...]
MSR Thesis Talk: Ravi Tej Akella
Title: Distributional Distance Classifiers for Goal-Conditioned Reinforcement Learning Abstract: Autonomous systems are increasingly being deployed in stochastic real-world environments. Often, these agents are trying to find the shortest path to a commanded goal. But what does it mean to find the shortest path in stochastic environments, where every strategy has a non-zero probability of failing? At [...]