Kiran Lekkala
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Kiran Lekkala has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Laurent Itti
Thomas Lord Department of Computer Science, University of Southern California
3 shared publications - Adam M. Jones
Independent Researcher, San Diego, CA, USA
2 shared publications - Ao Xu
Department of Computer Science, University of Southern California, Los Angeles, CA 90007, USA
2 shared publications - Di Wu
Department of Computer Science, University of Southern California, Los Angeles, CA 90007, USA
2 shared publications - Gozde Sahin
Department of Computer Science, University of Southern California, Los Angeles, CA 90007, USA
2 shared publications - Po-Hsuan Huang
Neuroscience Graduate Program, University of Southern California, Los Angeles, CA 90007, USA
2 shared publications
Latest Publications
- Open Access
Bird's Eye View Based Pretrained World model for Visual Navigation
Sim2Real transfer has gained popularity because it helps transfer from inexpensive simulators to real world. This paper presents a novel system that fuses components in a traditional World Model into a robust system, trained entirely within a simulator, that Zero-Shot transfers to the real world. To facilitate transfer, we use an intermediary representation that is based on \textit{Bird's Eye View (BEV)} images. Thus, our robot learns to navigate in a simulator by first learning to translate from complex \textit{First-Person View (FPV)} based RGB images to BEV representations, then learning to navigate using those representations. Later, when tested in the real world, the robot uses the perception model that translates FPV-based RGB images to embeddings that were learned by the FPV to BEV translator and that can be used by the downstream policy. The incorporation of state-checking modules using \textit{Anchor images} and Mixture Density LSTM not only interpolates uncertain and missing observations but also enhances the robustness of the model in the real-world. We trained the model using data from a Differential drive robot in the CARLA simulator. Our methodology's effectiveness is shown through the deployment of trained models onto a real-world Differential drive robot. Lastly we release a comprehensive codebase, dataset and models for training and deployment (\url{https://sites.google.com/view/value-explicit-pretraining}).
Open AccessBird's Eye View Based Pretrained World model for Visual Navigation
Sim2Real transfer has gained popularity because it helps transfer from inexpensive simulators to real world. This paper presents a novel system that fuses components in a traditional World Model into a robust system, trained entirely within a simulator, that Zero-Shot transfers to the real world. To facilitate transfer, we use an intermediary representation that is based on \textit{Bird's Eye View (BEV)} images. Thus, our robot learns to navigate in a simulator by first learning to translate from complex \textit{First-Person View (FPV)} based RGB images to BEV representations, then learning to navigate using those representations. Later, when tested in the real world, the robot uses the perception model that translates FPV-based RGB images to embeddings that were learned by the FPV to BEV translator and that can be used by the downstream policy. The incorporation of state-checking modules using \textit{Anchor images} and Mixture Density LSTM not only interpolates uncertain and missing observations but also enhances the robustness of the model in the real-world. We trained the model using data from a Differential drive robot in the CARLA simulator. Our methodology's effectiveness is shown through the deployment of trained models onto a real-world Differential drive robot. Lastly we release a comprehensive codebase, dataset and models for training and deployment (\url{https://sites.google.com/view/value-explicit-pretraining}).
- Open Access
USC-DCT: A Collection of Diverse Classification Tasks
Machine learning is a crucial tool for both academic and real-world applications. Classification problems are often used as the preferred showcase in this space, which has led to a wide variety of datasets being collected and utilized for a myriad of applications. Unfortunately, there is very little standardization in how these datasets are collected, processed, and disseminated. As new learning paradigms like lifelong or meta-learning become more popular, the demand for merging tasks for at-scale evaluation of algorithms has also increased. This paper provides a methodology for processing and cleaning datasets that can be applied to existing or new classification tasks as well as implements these practices in a collection of diverse classification tasks called USC-DCT. Constructed using 107 classification tasks collected from the internet, this collection provides a transparent and standardized pipeline that can be useful for many different applications and frameworks. While there are currently 107 tasks, USC-DCT is designed to enable future growth. Additional discussion provides explanations of applications in machine learning paradigms such as transfer, lifelong, or meta-learning, how revisions to the collection will be handled, and further tips for curating and using classification tasks at this scale.
Open AccessUSC-DCT: A Collection of Diverse Classification Tasks
Machine learning is a crucial tool for both academic and real-world applications. Classification problems are often used as the preferred showcase in this space, which has led to a wide variety of datasets being collected and utilized for a myriad of applications. Unfortunately, there is very little standardization in how these datasets are collected, processed, and disseminated. As new learning paradigms like lifelong or meta-learning become more popular, the demand for merging tasks for at-scale evaluation of algorithms has also increased. This paper provides a methodology for processing and cleaning datasets that can be applied to existing or new classification tasks as well as implements these practices in a collection of diverse classification tasks called USC-DCT. Constructed using 107 classification tasks collected from the internet, this collection provides a transparent and standardized pipeline that can be useful for many different applications and frameworks. While there are currently 107 tasks, USC-DCT is designed to enable future growth. Additional discussion provides explanations of applications in machine learning paradigms such as transfer, lifelong, or meta-learning, how revisions to the collection will be handled, and further tips for curating and using classification tasks at this scale.
- Open Access
Shaped Policy Search for Evolutionary Strategies using Waypoints
In this paper, we try to improve exploration in Blackbox methods, particularly Evolution strategies (ES), when applied to Reinforcement Learning (RL) problems where intermediate waypoints/subgoals are available. Since Evolutionary strategies are highly parallelizable, instead of extracting just a scalar cumulative reward, we use the state-action pairs from the trajectories obtained during rollouts/evaluations, to learn the dynamics of the agent. The learnt dynamics are then used in the optimization procedure to speed-up training. Lastly, we show how our proposed approach is universally applicable by presenting results from experiments conducted on Carla driving and UR5 robotic arm simulators.
Open AccessShaped Policy Search for Evolutionary Strategies using Waypoints
In this paper, we try to improve exploration in Blackbox methods, particularly Evolution strategies (ES), when applied to Reinforcement Learning (RL) problems where intermediate waypoints/subgoals are available. Since Evolutionary strategies are highly parallelizable, instead of extracting just a scalar cumulative reward, we use the state-action pairs from the trajectories obtained during rollouts/evaluations, to learn the dynamics of the agent. The learnt dynamics are then used in the optimization procedure to speed-up training. Lastly, we show how our proposed approach is universally applicable by presenting results from experiments conducted on Carla driving and UR5 robotic arm simulators.
- Open Access
Lightweight Learner for Shared Knowledge Lifelong Learning
In Lifelong Learning (LL), agents continually learn as they encounter new conditions and tasks. Most current LL is limited to a single agent that learns tasks sequentially. Dedicated LL machinery is then deployed to mitigate the forgetting of old tasks as new tasks are learned. This is inherently slow. We propose a new Shared Knowledge Lifelong Learning (SKILL) challenge, which deploys a decentralized population of LL agents that each sequentially learn different tasks, with all agents operating independently and in parallel. After learning their respective tasks, agents share and consolidate their knowledge over a decentralized communication network, so that, in the end, all agents can master all tasks. We present one solution to SKILL which uses Lightweight Lifelong Learning (LLL) agents, where the goal is to facilitate efficient sharing by minimizing the fraction of the agent that is specialized for any given task. Each LLL agent thus consists of a common task-agnostic immutable part, where most parameters are, and individual task-specific modules that contain fewer parameters but are adapted to each task. Agents share their task-specific modules, plus summary information ("task anchors") representing their tasks in the common task-agnostic latent space of all agents. Receiving agents register each received task-specific module using the corresponding anchor. Thus, every agent improves its ability to solve new tasks each time new task-specific modules and anchors are received. On a new, very challenging SKILL-102 dataset with 102 image classification tasks (5,033 classes in total, 2,041,225 training, 243,464 validation, and 243,464 test images), we achieve much higher (and SOTA) accuracy over 8 LL baselines, while also achieving near perfect parallelization. Code and data can be found at https://github.com/gyhandy/Shared-Knowledge-Lifelong-Learning
Open AccessLightweight Learner for Shared Knowledge Lifelong Learning
In Lifelong Learning (LL), agents continually learn as they encounter new conditions and tasks. Most current LL is limited to a single agent that learns tasks sequentially. Dedicated LL machinery is then deployed to mitigate the forgetting of old tasks as new tasks are learned. This is inherently slow. We propose a new Shared Knowledge Lifelong Learning (SKILL) challenge, which deploys a decentralized population of LL agents that each sequentially learn different tasks, with all agents operating independently and in parallel. After learning their respective tasks, agents share and consolidate their knowledge over a decentralized communication network, so that, in the end, all agents can master all tasks. We present one solution to SKILL which uses Lightweight Lifelong Learning (LLL) agents, where the goal is to facilitate efficient sharing by minimizing the fraction of the agent that is specialized for any given task. Each LLL agent thus consists of a common task-agnostic immutable part, where most parameters are, and individual task-specific modules that contain fewer parameters but are adapted to each task. Agents share their task-specific modules, plus summary information ("task anchors") representing their tasks in the common task-agnostic latent space of all agents. Receiving agents register each received task-specific module using the corresponding anchor. Thus, every agent improves its ability to solve new tasks each time new task-specific modules and anchors are received. On a new, very challenging SKILL-102 dataset with 102 image classification tasks (5,033 classes in total, 2,041,225 training, 243,464 validation, and 243,464 test images), we achieve much higher (and SOTA) accuracy over 8 LL baselines, while also achieving near perfect parallelization. Code and data can be found at https://github.com/gyhandy/Shared-Knowledge-Lifelong-Learning