Massachusetts Institute of TechnologyAcronym | MIT | Homepage | http://web.mit.edu/ | Country | [nothing] | ZIP, City | | Address | | Phone | | Type | Academy | Current organization | Massachusetts Institute of Technology | Child organizations | |
Open OpportunitiesReinforcement learning (RL) can potentially solve complex problems in a purely data-driven manner. Still, the state-of-the-art in applying RL in robotics, relies heavily on high-fidelity simulators. While learning in simulation allows to circumvent sample complexity challenges that are common in model-free RL, even slight distribution shift ("sim-to-real gap") between simulation and the real system can cause these algorithms to easily fail. Recent advances in model-based reinforcement learning have led to superior sample efficiency, enabling online learning without a simulator. Nonetheless, learning online cannot cause any damage and should adhere to safety requirements (for obvious reasons). The proposed project aims to demonstrate how existing safe model-based RL methods can be used to solve the foregoing challenges. - Engineering and Technology
- Master Thesis
| Gene therapies have the potential to enable the treatment of multiple currently incurable diseases, but delivery of these therapeutic molecules to the target tissue continues to present a major obstacle to their success and clinical translation. Our lab at Brigham and Women's Hospital has invented multiple novel drug delivery strategies, multiple of which have begun to be evaluated in human clinical trials. We are currently working to develop next-generation gene delivery platforms to accelerate the translation of these potentially transformative therapies to the clinic. - Biology, Chemistry, Materials Engineering, Pharmacology and Pharmaceutical Sciences
- Internship, Master Thesis
| The Traverso Lab at Brigham & Women's Hospital (Harvard Medical School) is focused on the development of commercializable products and technologies. One of our current interests is in leveraging computational and experimental methods to develop novel food products. We are seeking motivated and independent students to join our lab for their master's thesis. Students will be expected to develop competent physical models, simulate fluidics and mechanics, perform rheological tests, and validate theoretical models with experiments. Experience in these areas is beneficial but not necessary. We aim to recruit students with creativity, a willingness to learn, and the ability to work collaboratively on a team of interdisciplinary scientists and engineers. - Engineering and Technology
- Internship, Master Thesis
| The remarkable agility of animals, characterized by their rapid, fluid movements and precise interaction with their environment, serves as an inspiration for advancements in legged robotics. Recent progress in the field has underscored the potential of learning-based methods for robot control. These methods streamline the development process by optimizing control mechanisms directly from sensory inputs to actuator outputs, often employing deep reinforcement learning (RL) algorithms. By training in simulated environments, these algorithms can develop locomotion skills that are subsequently transferred to physical robots. Although this approach has led to significant achievements in achieving robust locomotion, mimicking the wide range of agile capabilities observed in animals remains a significant challenge. Traditionally, manually crafted controllers have succeeded in replicating complex behaviors, but their development is labor-intensive and demands a high level of expertise in each specific skill. Reinforcement learning offers a promising alternative by potentially reducing the manual labor involved in controller development. However, crafting learning objectives that lead to the desired behaviors in robots also requires considerable expertise, specific to each skill.
- Information, Computing and Communication Sciences
- Master Thesis
| Humanoid robots, designed to mimic the structure and behavior of humans, have seen significant advancements in kinematics, dynamics, and control systems. Teleoperation of humanoid robots involves complex control strategies to manage bipedal locomotion, balance, and interaction with environments. Research in this area has focused on developing robots that can perform tasks in environments designed for humans, from simple object manipulation to navigating complex terrains. Reinforcement learning has emerged as a powerful method for enabling robots to learn from interactions with their environment, improving their performance over time without explicit programming for every possible scenario. In the context of humanoid robotics and teleoperation, RL can be used to optimize control policies, adapt to new tasks, and improve the efficiency and safety of human-robot interactions. Key challenges include the high dimensionality of the action space, the need for safe exploration, and the transfer of learned skills across different tasks and environments. Integrating human motion tracking with reinforcement learning on humanoid robots represents a cutting-edge area of research. This approach involves using human motion data as input to train RL models, enabling the robot to learn more natural and human-like movements. The goal is to develop systems that can not only replicate human actions in real-time but also adapt and improve their responses over time through learning. Challenges in this area include ensuring real-time performance, dealing with the variability of human motion, and maintaining stability and safety of the humanoid robot.
- Information, Computing and Communication Sciences
- Master Thesis
| In recent years, advancements in reinforcement learning have achieved remarkable success in teaching robots discrete motor skills. However, this process often involves intricate reward structuring and extensive hyperparameter adjustments for each new skill, making it a time-consuming and complex endeavor. This project proposes the development of a skill generator operating within a continuous latent space. This innovative approach contrasts with the discrete skill learning methods currently prevalent in the field. By leveraging a continuous latent space, the skill generator aims to produce a diverse range of skills without the need for individualized reward designs and hyperparameter configurations for each skill. This method not only simplifies the skill generation process but also promises to enhance the adaptability and efficiency of skill learning in robotics. - Engineering and Technology, Information, Computing and Communication Sciences
- Master Thesis
| Recent advances in physically simulated humanoids have broadened their application spectrum, including animation, gaming, augmented and virtual reality (AR/VR), and robotics, showcasing significant enhancements in both performance and practicality. With the advent of motion capture (MoCap) technology and reinforcement learning (RL) techniques, these simulated humanoids are capable of replicating extensive human motion datasets, executing complex animations, and following intricate motion patterns using minimal sensor input. Nevertheless, generating such detailed and naturalistic motions requires meticulous motion data curation and the development of new physics-based policies from the ground up—a process that is not only labor-intensive but also fraught with challenges related to reward system design, dataset curation, and the learning algorithm, which can result in unnatural motions.
To circumvent these challenges, researchers have explored the use of latent spaces or skill embeddings derived from pre-trained motion controllers, facilitating their application in hierarchical RL frameworks. This method involves training a low-level policy to generate a representation space from tasks like motion imitation or adversarial learning, which a high-level policy can then navigate to produce latent codes that represent specific motor actions. This approach promotes the reuse of learned motor skills and efficient action space sampling. However, the effectiveness of this strategy is often limited by the scope of the latent space, which is traditionally based on specialized and relatively narrow motion datasets, thus limiting the range of achievable behaviors.
An alternative strategy involves employing a low-level controller as a motion imitator, using full-body kinematic motions as high-level control signals. This method is particularly prevalent in motion tracking applications, where supervised learning techniques are applied to paired input data, such as video and kinematic data. For generative tasks without paired data, RL becomes necessary, although kinematic motion presents challenges as a sampling space due to its high dimensionality and the absence of physical constraints. This necessitates the use of kinematic motion latent spaces for generative tasks and highlights the limitations of using purely kinematic signals for tasks requiring interaction with the environment or other agents, where understanding of interaction dynamics is crucial.
We would like to extend the idea of creating a low-level controller as a motion imitator to full-body motions from real-time expressive kinematic targets. - Engineering and Technology, Information, Computing and Communication Sciences
- Master Thesis
| In the burgeoning field of deep reinforcement learning (RL), agents autonomously develop complex behaviors through a process of trial and error. Yet, the application of RL across various domains faces notable hurdles, particularly in devising appropriate reward functions. Traditional approaches often resort to sparse rewards for simplicity, though these prove inadequate for training efficient agents. Consequently, real-world applications may necessitate elaborate setups, such as employing accelerometers for door interaction detection, thermal imaging for action recognition, or motion capture systems for precise object tracking. Despite these advanced solutions, crafting an ideal reward function remains challenging due to the propensity of RL algorithms to exploit the reward system in unforeseen ways. Agents might fulfill objectives in unexpected manners, highlighting the complexity of encoding desired behaviors, like adherence to social norms, into a reward function.
An alternative strategy, imitation learning, circumvents the intricacies of reward engineering by having the agent learn through the emulation of expert behavior. However, acquiring a sufficient number of high-quality demonstrations for this purpose is often impractically costly. Humans, in contrast, learn with remarkable autonomy, benefiting from intermittent guidance from educators who provide tailored feedback based on the learner's progress. This interactive learning model holds promise for artificial agents, offering a customized learning trajectory that mitigates reward exploitation without extensive reward function engineering. The challenge lies in ensuring the feedback process is both manageable for humans and rich enough to be effective. Despite its potential, the implementation of human-in-the-loop (HiL) RL remains limited in practice. Our research endeavors to significantly lessen the human labor involved in HiL learning, leveraging both unsupervised pre-training and preference-based learning to enhance agent development with minimal human intervention. - Engineering and Technology, Information, Computing and Communication Sciences
- Master Thesis
| Ingestable and implantable robots that can reside in the human body for long term are revolutionizing the future of personalized medicine. However, one of the most significant challenges facing the widespread adoption of these devices is ensuring a reliable and sustainable power source.Traditional power sources, such as batteries, are impractical for long-term use within these robots due to size constraints, limited energy capacity, and the need for repeated invasive procedures for replacement.
In the Traverso Lab at Brigham and Women’s Hospital (Harvard Medical School), We are exploring advanced engineering approaches to develop novel wireless power transfer (WPT) systems as sustainable powering sources.
- Biomedical Engineering
- Internship, Master Thesis
| The surface of the gastrointestinal (GI) tract is covered by a mucosal membrane, consisting of enormous health-related biochemical, physiologic, and pathophysiologic information, and serving for nutrition exchange. Progress has been made to access the GI mucosa for diagnostics and therapeutics in clinical settings. However, it is still extremely challenging to build a biocompatible and robust GI mucosa interface enabling real-time, continuous, and minimally invasive interactions with human body, due to the constant GI motility, fast cellular turnover rate, limited cavity space and extremely chemical and biological environments
In the Traverso Laboratories at Brigham and Women’s Hospital (Harvard Medical School), We are exploring novel engineering approaches to develop robust mucosal interfaces for long-term deployment of micro-electronics/drug reservoirs/physical barriers in the GI tract.
- Biomaterials, Biomechanical Engineering, Mechanical Engineering, Polymers
- Master Thesis
|
|