publications

2026

1. Learning to Drive on Mars: Visual Multimodal Traversability Estimation for Off-World Navigation

   Darren Chiu ,  Cole Wilson ,  Andrei Tumbar ,  Gaurav S. Sukhatme ,  and  Steven Myint

   2026

   Abs arXiv Bib

   Autonomous navigation on Mars requires vehicles to distinguish between traversable terrains across diverse and visually challenging environments. However, progress in learning-based navigation for off-world environments has been limited by the lack of large-scale datasets. Since landing in Jezero Crater, the Mars 2020 Perseverance rover has traversed terrain ranging from sandy dunes, rocky patches, and flat bedrocks. As a result, this paper presents a dataset spanning 500 sols and 45km of trajectories driven by both human operators and the onboard planner, ENav. Our dataset contains grayscale stereo image pairs, poses, accelerometer readings, rocker-bogie angles, and estimates of tilt and wheel slip. Building on this dataset, we introduce an uncertainty-aware traversability-estimation framework that learns terrain representations from multimodal driving experience. We compare our proposed method against existing approaches on the Mars 2020 dataset and show that our method achieves an AUROC of 0.874 and an F1 score of 0.758, outperforming the strongest baseline by 0.058 and 0.156, respectively, while also achieving the highest average precision and recall. Finally, we show that the visual representations can be integrated into path planners, such as ENav, on a physical rover test bed.

   @misc{chiu2026learningdrivemarsvisual,
     title = {Learning to Drive on Mars: Visual Multimodal Traversability Estimation for Off-World Navigation},
     author = {Chiu, Darren and Wilson, Cole and Tumbar, Andrei and Sukhatme, Gaurav S. and Myint, Steven},
     year = {2026},
     eprint = {2609.24952},
     archiveprefix = {arXiv},
     primaryclass = {cs.RO},
     url = {https://arxiv.org/abs/2609.24952},
   }

2. Steering Multirobot Behavior via Closed-Loop Affine Activation Editing

   Satyajeet Das ,  Darren Chiu ,  Shashank Hegde ,  and  Gaurav S. Sukhatme

   2026

   Abs arXiv Bib

   Real-world robots need to adapt their behavior beyond the envelope of their pre-trained policy. Policy finetuning or retraining are options, but they risk catastrophic forgetting, degrading the pretrained policy’s base performance. To combat this, we introduce CLAE: Closed-Loop Affine Activation Editing, an inference-time framework for steering the behavior of a frozen policy by editing intermediate activations while keeping the base policy weights and downstream action head untouched. CLAE approaches behavior steering as a closed-loop problem whose outputs edit policy activations that adapt online to the robot state, environment, target behavior, and multi-robot context. It trains a sparse autoencoder over frozen-policy activations, selects behavior-relevant latent features via post-hoc probing, and learns a lightweight RL-based steering policy that applies state-dependent affine edits to selected latents during inference. We validate CLAE on a frozen multi-quadrotor navigation policy trained to perform a single task: navigating robots to a set of goal locations while avoiding obstacles. Through extensive simulations and physical tests, we show that while navigating to their goal positions, CLAE can 1. steer individual robot behavior by controlling each robot’s velocity profile; 2. coordinate multirobot behavior by preserving a desired formation; and 3. produce entirely new behavior wherein robots are required to reduce their exposure to surveillance cameras in the environment.

   @misc{das2026steeringmultirobotbehaviorclosedloop,
     title = {Steering Multirobot Behavior via Closed-Loop Affine Activation Editing},
     author = {Das, Satyajeet and Chiu, Darren and Hegde, Shashank and Sukhatme, Gaurav S.},
     year = {2026},
     eprint = {2606.11489},
     archiveprefix = {arXiv},
     primaryclass = {cs.RO},
     url = {https://arxiv.org/abs/2606.11489},
   }

3. Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation

   Satyajeet Das ,  Darren Chiu ,  Zhehui Huang ,  Lars Lindemann ,  and  Gaurav S. Sukhatme

   2026

   Abs arXiv Bib

   Reinforcement learning has enabled significant progress in complex domains such as coordinating and navigating multiple quadrotors. However, even well-trained policies remain vulnerable to collisions in obstacle-rich environments. Addressing these infrequent but critical safety failures through retraining or fine-tuning is costly and risks degrading previously learned skills. Inspired by activation steering in large language models and latent editing in computer vision, we introduce a framework for inference-time Latent Activation Editing (LAE) that refines the behavior of pre-trained policies without modifying their weights or architecture. The framework operates in two stages: (i) an online classifier monitors intermediate activations to detect states associated with undesired behaviors, and (ii) an activation editing module that selectively modifies flagged activations to shift the policy towards safer regimes. In this work, we focus on improving safety in multi-quadrotor navigation. We hypothesize that amplifying a policy’s internal perception of risk can induce safer behaviors. We instantiate this idea through a latent collision world model trained to predict future pre-collision activations, thereby prompting earlier and more cautious avoidance responses. Extensive simulations and real-world Crazyflie experiments demonstrate that LAE achieves statistically significant reduction in collisions (nearly 90% fewer cumulative collisions compared to the unedited baseline) and substantially increases the fraction of collision-free trajectories, while preserving task completion. More broadly, our results establish LAE as a lightweight paradigm, feasible on resource-constrained hardware, for post-deployment refinement of learned robot policies.

   @misc{das2025latentactivationeditinginferencetime,
     title = {Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation},
     author = {Das, Satyajeet and Chiu, Darren and Huang, Zhehui and Lindemann, Lars and Sukhatme, Gaurav S.},
     year = {2026},
     booktitle = {2026 IEEE International Conference on Robotics and Automation (ICRA)},
     eprint = {2509.20623},
     archiveprefix = {arXiv},
     primaryclass = {cs.RO},
     url = {https://arxiv.org/abs/2509.20623},
   }

2025

1. LEARN: Learning End-to-End Aerial Resource-Constrained Multi-Robot Navigation

   Darren Chiu ,  Zhehui Huang ,  Ruohai Ge ,  and  Gaurav S. Sukhatme

   2025

   Abs arXiv Bib

   Nano-UAV teams offer great agility yet face severe navigation challenges due to constrained onboard sensing, communication, and computation. Existing approaches rely on high-resolution vision or compute intensive planners, rendering them infeasible for these platforms. We introduce LEARN, a lightweight, two-stage safety-guided reinforcement learning (RL) framework for multi-UAV navigation in cluttered spaces. Our system combines low-resolution Time-of-Flight (ToF) sensors and a simple motion planner with a compact, attention-based RL policy. In simulation, LEARN outperforms two state-of-the-art planners by 10% while using substantially fewer resources. We demonstrate LEARN’s viability on six Crazyflie quadrotors, achieving fully onboard flight in diverse indoor and outdoor environments at speeds up to 2.0m/s and traversing 0.2m gaps.

   @misc{chiu2025learnlearningendtoendaerial,
     title = {LEARN: Learning End-to-End Aerial Resource-Constrained Multi-Robot Navigation},
     author = {Chiu, Darren and Huang, Zhehui and Ge, Ruohai and Sukhatme, Gaurav S.},
     year = {2025},
     eprint = {2511.17765},
     archiveprefix = {arXiv},
     primaryclass = {cs.RO},
     url = {https://arxiv.org/abs/2511.17765},
   }

2. SAFE-GIL: SAFEty Guided Imitation Learning for Robotic Systems

   Yusuf Umut Ciftci ,  Darren Chiu ,  Zeyuan Feng ,  Gaurav S. Sukhatme ,  and  Somil Bansal

   In 2025 IEEE International Conference on Robotics and Automation (ICRA) , 2025

   Abs arXiv Bib

   Behavior cloning (BC) is a widely-used approach in imitation learning, where a robot learns a control policy by observing an expert supervisor. However, the learned policy can make errors and might lead to safety violations, which limits their utility in safety-critical robotics applications. While prior works have tried improving a BC policy via additional real or synthetic action labels, adversarial training, or runtime filtering, none of them explicitly focus on reducing the BC policy’s safety violations during training time. We propose SAFE-GIL, a design-time method to learn safety-aware behavior cloning policies. SAFE-GIL deliberately injects adversarial disturbance in the system during data collection to guide the expert towards safety-critical states. This disturbance injection simulates potential policy errors that the system might encounter during the test time. By ensuring that training more closely replicates expert behavior in safety-critical states, our approach results in safer policies despite policy errors during the test time. We further develop a reachability-based method to compute this adversarial disturbance. We compare SAFE-GIL with various behavior cloning techniques and online safety-filtering methods in three domains: autonomous ground navigation, aircraft taxiing, and aerial navigation on a quadrotor testbed. Our method demonstrates a significant reduction in safety failures, particularly in low data regimes where the likelihood of learning errors, and therefore safety violations, is higher.

   @inproceedings{11128298,
     author = {Ciftci, Yusuf Umut and Chiu, Darren and Feng, Zeyuan and Sukhatme, Gaurav S. and Bansal, Somil},
     booktitle = {2025 IEEE International Conference on Robotics and Automation (ICRA)},
     title = {SAFE-GIL: SAFEty Guided Imitation Learning for Robotic Systems},
     year = {2025},
     volume = {},
     number = {},
     pages = {3559-3566},
     keywords = {Training;Runtime;Filtering;Imitation learning;Cloning;Data collection;Aircraft navigation;Safety;Robots;Quadrotors},
     doi = {10.1109/ICRA55743.2025.11128298},
   }

2024

1. Collective Bayesian Decision-Making in a Swarm of Miniaturized Robots for Surface Inspection

   Thiemen Siemensma ,  Darren Chiu ,  Sneha Ramshanker ,  Radhika Nagpal ,  and  Bahar Haghighat

   In Swarm Intelligence , 2024

   Abs arXiv Bib

   Robot swarms can effectively serve a variety of sensing and inspection applications. Certain inspection tasks require a binary classification decision. This work presents an experimental setup for a surface inspection task based on vibration sensing and studies a Bayesian two-outcome decision-making algorithm in a swarm of miniaturized wheeled robots. The robots are tasked with individually inspecting and collectively classifying a }}1\backslash,\backslashtext {m} \backslashtimes 1\backslash,\backslashtext {m}}}1m\texttimes1mtiled surface consisting of vibrating and non-vibrating tiles based on the majority type of tiles. The robots sense vibrations using onboard IMUs and perform collision avoidance using a set of IR sensors. We develop a simulation and optimization framework leveraging the Webots robotic simulator and a Particle Swarm Optimization (PSO) method. We consider two existing information sharing strategies and propose a new one that allows the swarm to rapidly reach accurate classification decisions. We first find optimal parameters that allow efficient sampling in simulation and then evaluate our proposed strategy against the two existing ones using 100 randomized simulation and 10 real experiments. We find that our proposed method compels the swarm to make decisions at an accelerated rate, with an improvement of up to 20.52% in mean decision time at only 0.78% loss in accuracy.

   @inproceedings{10.1007/978-3-031-70932-6_5,
     author = {Siemensma, Thiemen and Chiu, Darren and Ramshanker, Sneha and Nagpal, Radhika and Haghighat, Bahar},
     title = {Collective Bayesian Decision-Making in a Swarm of Miniaturized Robots for Surface Inspection},
     booktitle = {Swarm Intelligence},
     year = {2024},
     publisher = {Springer Nature Switzerland},
     address = {Cham},
     pages = {57--70},
     isbn = {978-3-031-70932-6},
   }

2. Optimization and Evaluation of a Multi Robot Surface Inspection Task Through Particle Swarm Optimization

   Darren Chiu ,  Radhika Nagpal ,  and  Bahar Haghighat

   In 2024 IEEE International Conference on Robotics and Automation (ICRA) , 2024

   Abs arXiv Bib

   Robot swarms can be tasked with a variety of automated sensing and inspection applications in aerial, aquatic, and surface environments. In this paper, we study a simplified two-outcome surface inspection task. We task a group of robots to inspect and collectively classify a 2D surface section based on a binary pattern projected on the surface. We use a decentralized Bayesian decision-making algorithm and deploy a swarm of 3-cm sized wheeled robots to inspect a randomized black and white tiled surface section of size 1mx1m in simulation. We first describe the model parameters that characterize our simulated environment, the robot swarm, and the inspection algorithm. We then employ a noise-resistant heuristic optimization scheme based on the Particle Swarm Optimization (PSO) using a fitness evaluation that combines the swarms classification decision accuracy and decision time. We use our fitness measure definition to asses the optimized parameters through 100 randomized simulations that vary surface pattern and initial robot poses. The optimized algorithm parameters show up to 55% improvement in median of fitness evaluations against an empirically chosen parameter set.

   @inproceedings{10611661,
     author = {Chiu, Darren and Nagpal, Radhika and Haghighat, Bahar},
     booktitle = {2024 IEEE International Conference on Robotics and Automation (ICRA)},
     title = {Optimization and Evaluation of a Multi Robot Surface Inspection Task Through Particle Swarm Optimization},
     year = {2024},
     volume = {},
     number = {},
     pages = {8996-9002},
     keywords = {Decision making;Inspection;Robot sensing systems;Particle measurements;Classification algorithms;Sensors;Mobile robots},
     doi = {10.1109/ICRA57147.2024.10611661},
   }