publications

2025

1. 

   Diagnostic Runtime Monitoring with Martingales

   A. Hindy, R. Luo, S. Banerjee, and 3 more authors

   2025

   Preprint, arXiv:2407.21748

   Abs arXiv

   Machine learning systems deployed in safety-critical robotics settings must be robust to distribution shifts. However, system designers must understand the \textitcause of a distribution shift in order to implement the appropriate intervention or mitigation strategy and prevent system failure. In this paper, we present a novel framework for diagnosing distribution shifts in a streaming fashion by deploying multiple stochastic martingales simultaneously. We show that knowledge of the underlying cause of a distribution shift can lead to proper interventions over the lifecycle of a deployed system. Our experimental framework can easily be adapted to different types of distribution shifts, models, and datasets. We find that our method outperforms existing work on diagnosing distribution shifts in terms of speed, accuracy, and flexibility, and validate the efficiency of our model in both simulated and live hardware settings.

2. 

   Deep Learning Warm Starts for Trajectory Optimization on the International Space Station

   S. Banerjee, A. Cauligi, and M. Pavone

   In Int. Conf. on Space Robotics, 2025

   Abs arXiv Website

   Although widely used in commercial and industrial robotics, trajectory optimization has seen limited use in space applications due to its high computational demands. In this work, we present flight results from experiments with the Astrobee free-flying robot on board the International Space Station (ISS), that demonstrate how machine learning can accelerate on-board trajectory optimization while preserving theoretical solver guarantees. To the best of the authors’ knowledge, this is the first-ever demonstration of learning-based control on the ISS. Our approach leverages the GuSTO sequential convex programming framework and uses a neural network, trained offline, to map problem parameters to effective initial “warm-start” trajectories, paving the way for faster real-time optimization on resource-constrained space platforms.

3. 

   CORA: Concept Study for a New Frontiers Ceres Habitability Mission

   T. A. Plattner, I. Mishra, S. Banerjee, and 16 more authors

   2025

   In preparation

   Abs

   Ceres, the largest object in the asteroid belt, is a relict ocean world with recent geological activity, including water vapor and bright evaporite deposits linked to simple organics. We propose a lander mission to investigate Ceres’ exosphere, subsurface, organics, and astrobiological potential. Key objectives include determining the source of water vapor, assessing interior hydrothermal processes, evaluating the origin of complex organics, and analyzing evaporite deposits for life-essential elements. A suite of instruments—including a UV imaging spectrometer, GC-MS, X-ray spectrometer, magnetotelluric sounder, and cameras—would enable orbital and in-situ studies. Launch in the early 2030s would allow  11 months of orbital reconnaissance and  1 month of landed operations, providing unprecedented insights into Ceres and ocean worlds more broadly.

2024

1. 

   Contingency Planning Using Bi-level Markov Decision Processes for Space Missions

   S. Banerjee, B. Balaban, M. Shirley, and 2 more authors

   In IEEE Aerospace Conference, 2024

   Abs arXiv

   This work focuses on autonomous contingency planning for scientific missions by enabling rapid policy computation from any off-nominal point in the state space in the event of a delay or deviation from the nominal mission plan. Successful contingency planning involves managing risks and rewards, often probabilistically associated with actions, in stochastic scenarios. Markov Decision Processes (MDPs) are used to mathematically model decision-making in such scenarios. However, in the specific case of planetary rover traverse planning, the vast action space and long planning time horizon pose computational challenges. A bi-level MDP framework is proposed to improve computational tractability, while also aligning with existing mission planning practices and enhancing explainability and trustworthiness of AI-driven solutions. We discuss the conversion of a mission planning MDP into a bi-level MDP, and test the framework on RoverGridWorld, a modified GridWorld environment for rover mission planning. We demonstrate the computational tractability and near-optimal policies achievable with the bi-level MDP approach, highlighting the trade-offs between compute time and policy optimality as the problem’s complexity grows. This work facilitates more efficient and flexible contingency planning in the context of scientific missions.

2. Learning-Enabled Adaptation and Planning for Space Robotics

   S. Banerjee

   Stanford University, 2024
3. Adapting a Foundation Model for Space-based Tasks

   M. Foutter, P. Bhoj, R. Sinha, and 8 more authors

   2024

   arXiv:2408.05924
4. A Concept for a New Frontiers Class Ceres Lander

   I. Mishra, T. Plattner, S. Banerjee, and 16 more authors

   American Geophysical Union (AGU), 2024
5. System Health Enabled Realtime Planning Advisor (SHERPA) and Its Use in Lunar Exploration

   E Balaban, S Banerjee, Z Booth, and 7 more authors

   Lunar and Planetary Institute (LPI) Contributions, 2024

2023

1. Self-Supervised Model Generalization using Out-of-Distribution Detection

   M. Foutter, R. Sinha, S. Banerjee, and 1 more author

   In Conf. on Robot Learning - Workshop on Out-of-Distribution Generalization in Robotics, 2023

2. 

   Data Lifecycle Management in Evolving Input Distributions for Learning-based Aerospace Applications

   S. Banerjee, A. Sharma, E. Schmerling, and 3 more authors

   In IEEE Aerospace Conference, 2023

   Abs arXiv

   As input distributions evolve over a mission lifetime, maintaining performance of learning-based models becomes challenging. This paper presents a framework to incrementally retrain a model by selecting a subset of test inputs to label, which allows the model to adapt to changing input distributions. Algorithms within this framework are evaluated based on (1) model performance throughout mission lifetime and (2) cumulative costs associated with labeling and model retraining. We provide an open-source benchmark of a satellite pose estimation model trained on images of a satellite in space and deployed in novel scenarios (e.g., different backgrounds or misbehaving pixels), where algorithms are evaluated on their ability to maintain high performance by retraining on a subset of inputs. We also propose a novel algorithm to select a diverse subset of inputs for labeling, by characterizing the information gain from an input using Bayesian uncertainty quantification and choosing a subset that maximizes collective information gain using concepts from batch active learning. We show that our algorithm outperforms others on the benchmark, e.g., achieves comparable performance to an algorithm that labels 100% of inputs, while only labeling 50% of inputs, resulting in low costs and high performance over the mission lifetime.

2022

1. 

   A System-Level View on Out-of-Distribution Data in Robotics

   R. Sinha, S. Sharma, S. Banerjee, and 6 more authors

   2022

   Preprint, arXiv:2212.14020

   Abs arXiv

   When testing conditions differ from those represented in training data, so-called out-of-distribution (OOD) inputs can mar the reliability of black-box learned components in the modern robot autonomy stack. Therefore, coping with OOD data is an important challenge on the path towards trustworthy learning-enabled open-world autonomy. In this paper, we aim to demystify the topic of OOD data and its associated challenges in the context of data-driven robotic systems, drawing connections to emerging paradigms in the ML community that study the effect of OOD data on learned models in isolation. We argue that as roboticists, we should reason about the overall system-level competence of a robot as it performs tasks in OOD conditions. We highlight key research questions around this system-level view of OOD problems to guide future research toward safe and reliable learning-enabled autonomy.

2. 

   VIPER Traverse Planning

   M Shirley, E Balaban, A Colaprete, and 6 more authors

   In 53rd Lunar and Planetary Science Conference (LPSC), 2022

   PDF Website

2020

1. 

   Learning-based Warm-Starting for Fast Sequential Convex Programming and Trajectory Optimization

   S. Banerjee, T. Lew, R. Bonalli, and 4 more authors

   In IEEE Aerospace Conference, Mar 2020

   Abs PDF

   Sequential convex programming (SCP) has recently emerged as an effective tool to quickly compute locally optimal trajectories for robotic and aerospace systems alike, even when initialized with an unfeasible trajectory. In this paper, by focusing on the Guaranteed Sequential Trajectory Optimization (GuSTO) algorithm, we propose a methodology to accelerate SCP-based algorithms through warm-starting. Specifically, leveraging a dataset of expert trajectories from GuSTO, we devise a neural-network-based approach to predict a locally optimal state and control trajectory, which is used to warm-start the SCP algorithm. This approach allows one to retain all the theoretical guarantees of GuSTO while simultaneously taking advantage of the fast execution of the neural network and reducing the time and number of iterations required for GuSTO to converge. The result is a faster and theoretically guaranteed trajectory optimization algorithm.

2. 

   Adaptive Meta-Learning for Identification of Rover-Terrain Dynamics

   S. Banerjee, J. Harrison, P. M. Furlong, and 1 more author

   In Int. Symp. on Artificial Intelligence, Robotics and Automation in Space, Oct 2020

   Abs arXiv

   Rovers require knowledge of terrain to plan trajectories that maximize safety and efficiency. Terrain type classification relies on input from human operators or machine learning-based image classification algorithms. However, high level terrain classification is typically not sufficient to prevent incidents such as rovers becoming unexpectedly stuck in a sand trap; in these situations, online rover-terrain interaction data can be leveraged to accurately predict future dynamics and prevent further damage to the rover. This paper presents a meta-learning-based approach to adapt probabilistic predictions of rover dynamics by augmenting a nominal model affine in parameters with a Bayesian regression algorithm (P-ALPaCA). A regularization scheme is introduced to encourage orthogonality of nominal and learned features, leading to interpretable probabilistic estimates of terrain parameters in varying terrain conditions.

2019

1. Electric Field Polarization of Electromagnetic Radiation from Micrometeoroid and Dust Impacts on Spacecraft

   S. A. Q. Young, N. Lee, B. Estacio, and 5 more authors

   In AGU Fall Meeting Abstracts, Oct 2019
2. Characterization of the Plasma Plume Produced by Dust and Meteoroid Impact of Different Materials

   B. Estacio, N. Lee, G. Shohet, and 5 more authors

   In AGU Fall Meeting Abstracts, Oct 2019
3. Characterization of Optical Emission from Ground-Based Hypervelocity Impact Experiments

   I. Matthews, N. Lee, G. Shohet, and 5 more authors

   In AGU Fall Meeting Abstracts, Oct 2019
4. Dusty plasma effects in hypervelocity impacts on the ground and in space

   G. Shohet, N. Lee, B. Estacio, and 5 more authors

   In AGU Fall Meeting Abstracts, Oct 2019