AIConfPaper
← Search

Arun Kumar Singh

32 accepted papers

2026

Crowd-FM: Learned Optimal Selection of Conditional Flow Matching-Generated Trajectories for Crowd Navigation

Antareep Singha, Laksh Nanwani, Mathai Mathew Pulicken, Samkit Jain, Phani Teja Singamaneni, Arun Kumar Singh +1
ICRA 2026poster

Safe and computationally efficient local planning for mobile robots in dense, unstructured human crowds remains a fundamental challenge. Moreover, ensuring that robot trajectories are similar to how a human moves will increase the acceptance of the robot in human environments. In this paper, we pres…

Cited by 0Source ↗PDF ↗Scholar ↗
2026

MMD-OPT : Maximum Mean Discrepancy Based Sample Efficient Collision Risk Minimization for Autonomous Driving (I)

Basant Sharma, Arun Kumar Singh
ICRA 2026poster

We propose MMD-OPT: a sample-efficient approach for minimizing the risk of collision under arbitrary prediction distribution of the dynamic obstacles. MMD-OPT is based on embedding distribution in Reproducing Kernel Hilbert Space (RKHS) and the associated Maximum Mean Discrepancy (MMD). We show how …

Cited by 0Scholar ↗
2026

MonoMPC: Monocular Vision Based Navigation With Learned Collision Model and Risk-Aware Model Predictive Control

Basant Sharma, Prajyot Jadhav, Pranjal Paul, K. Madhava Krishna, Arun Kumar Singh
RA-L 2026

Navigating unknown environments with a single RGB camera is challenging, as the lack of depth information prevents reliable collision-checking. While some methods use estimated depth to build collision maps, we found that depth estimates from vision foundation models are too noisy for zero-shot navi

Cited by 1Source ↗Scholar ↗
2026

MonoMPC: Monocular Vision Based Navigation with Learned Collision Model and Risk-Aware Model Predictive Control

Basant Sharma, Prajyot Jadhav, Pranjal Paul, Madhava Krishna, Arun Kumar Singh
ICRA 2026poster

Navigating unknown environments with a single RGB camera is challenging, as the lack of depth information prevents reliable collision-checking. While some methods use estimated depth to build collision maps, we found that depth estimates from vision foundation models are too noisy for zero-shot navi…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

$\pi$-MPPI: A Projection-Based Model Predictive Path Integral Scheme for Smooth Optimal Control of Fixed-Wing Aerial Vehicles

Edvin Martin Andrejev, Amith Manoharan, Karl-Eerik Unt, Arun Kumar Singh
RA-L 2025

Model Predictive Path Integral (MPPI) is a popular sampling-based Model Predictive Control (MPC) algorithm for nonlinear systems. It optimizes trajectories by sampling control sequences and averaging them. However, a key issue with MPPI is the non-smoothness of the optimal control sequence, leading

Cited by 6Source ↗Scholar ↗
2025

CrowdSurfer: Sampling Optimization Augmented with Vector-Quantized Variational AutoEncoder for Dense Crowd Navigation

Naman Kumar, Antareep Singha, Laksh Nanwani, Dhruv Potdar, Tarun R, Fatemeh Rastgar +3
ICRA 2025

Navigation amongst densely packed crowds remains a challenge for mobile robots. The complexity increases further if the environment layout changes, making the prior computed global plan infeasible. In this paper, we show that it is possible to dramatically enhance crowd navigation by just improving

Cited by 1Source ↗code ↗Scholar ↗
2025

Da-Vil: Adaptive Dual-Arm Manipulation with Reinforcement Learning and Variable Impedance Control

Md Faizal Karim, Shreya Bollimuntha, Mohammed Saad Hashmi, Autrio Das, Gaurav Singh, Srinath Sridhar +3
ICRA 2025

Dual-arm manipulation is an area of growing interest in the robotics community. Enabling robots to perform tasks that require the coordinated use of two arms, is essential for complex manipulation tasks such as handling large objects, assembling components, and performing human-like interactions. Ho

Cited by 13Source ↗code ↗Scholar ↗
2025

Diffusion-FS: Multimodal Free-Space Prediction via Diffusion for Autonomous Driving

Keshav Gupta, Tejas S. Stanley, Pranjal Paul, Arun Kumar Singh, Madhava Krishna
IROS 2025

Drivable Free-space prediction is a fundamental and crucial problem in autonomous driving. Recent works have addressed the problem by representing the entire non-obstacle road regions as the free-space. In contrast our aim is to estimate the driving corridors that are a navigable subset of the entir

Cited by 1Source ↗Scholar ↗
2024

AMSwarmX: Safe Swarm Coordination in CompleX Environments via Implicit Non-Convex Decomposition of the Obstacle-Free Space

Vivek K. Adajania, Siqi Zhou, Arun Kumar Singh, Angela P. Schoellig
ICRA 2024poster

Quadrotor motion planning in complex environments leverage the concept of safe flight corridor (SFC) to facilitate static obstacle avoidance. Typically, SFCs are constructed through convex decomposition of the environment’s free space into cuboids, convex polyhedra, or spheres. However, such SFCs ca…

Cited by 5Source ↗code ↗Scholar ↗
2024

Bi-level Trajectory Optimization on Uneven Terrains with Differentiable Wheel-Terrain Interaction Model

Amith Manoharan, Aditya Sharma, Himani Belsare, Kaustab Pal, K. Madhava Krishna, Arun Kumar Singh
IROS 2024poster

Navigation of wheeled vehicles on uneven terrain necessitates going beyond the 2D approaches for trajectory planning. Specifically, it is essential to incorporate the full 6dof variation of vehicle pose and its associated stability cost in the planning process. To this end, most recent works aim to…

Cited by 3Source ↗Scholar ↗
2024

Differentiable-Optimization Based Neural Policy for Occlusion-Aware Target Tracking

Houman Masnavi, Arun Kumar Singh, Farrokh Janabi-Sharifi
RA-L 2024

We propose a learned probabilistic neural policy for safe, occlusion-free target tracking. The core novelty of our work stems from the structure of our policy network that combines generative modeling based on Conditional Variational Autoencoder (CVAE) with differentiable optimization layers. The we

Cited by 3Source ↗code ↗Scholar ↗
2024

LeGo-Drive: Language-enhanced Goal-oriented Closed-Loop End-to-End Autonomous Driving

Pranjal Paul, Anant Garg, Tushar Choudhary, Arun Kumar Singh, K. Madhava Krishna
IROS 2024poster

Existing Vision-Language Models (VLMs) produce long-term trajectory waypoints or directly control actions based on their perception input and language prompt. However, these VLMs are not explicitly aware of the constraints imposed by the scene or kinematics of the vehicle. As a result, the generated…

Cited by 3Source ↗Scholar ↗
2024

Learning Sampling Distribution and Safety Filter for Autonomous Driving with VQ-VAE and Differentiable Optimization

Simon Idoko, Basant Sharma, Arun Kumar Singh
IROS 2024poster

Sampling trajectories from a distribution followed by ranking them based on a specified cost function is a common approach in autonomous driving. Typically, the sampling distribution is hand-crafted (e.g a Gaussian, or a grid). Recently, there have been efforts towards learning the sampling distribu…

Cited by 2Source ↗code ↗Scholar ↗
2024

PRIEST: Projection Guided Sampling-Based Optimization for Autonomous Navigation

Fatemeh Rastgar, Houman Masnavi, Basant Sharma, Alvo Aabloo, Jan Swevers, Arun Kumar Singh
RA-L 2024

Efficient navigation in unknown and dynamic environments is crucial for expanding the application domain of mobile robots. The core challenge stems from the non-availability of a feasible global path for guiding optimization-based local planners. As a result, existing local planners often get trappe

Cited by 11Source ↗code ↗Scholar ↗
2023

AMSwarm: An Alternating Minimization Approach for Safe Motion Planning of Quadrotor Swarms in Cluttered Environments

Vivek K. Adajania, Siqi Zhou, Arun Kumar Singh, Angela P. Schoellig
ICRA 2023poster

This paper presents a scalable online algorithm to generate safe and kinematically feasible trajectories for quadrotor swarms. Existing approaches rely on linearizing Euclidean distance-based collision constraints and on axis-wise decoupling of kinematic constraints to reduce the trajectory optimiza…

Cited by 21Source ↗code ↗Scholar ↗
2023

End-to-End Learning of Behavioural Inputs for Autonomous Driving in Dense Traffic

Jatan Shrestha, Simon Idoko, Basant Sharma, Arun Kumar Singh
IROS 2023poster

Trajectory sampling in the Frenet(road-aligned) frame, is one of the most popular methods for motion planning of autonomous vehicles. It operates by sampling a set of behavioral inputs, such as lane offset and forward speed, before solving a trajectory optimization problem conditioned on the sampled…

Cited by 5Source ↗code ↗Scholar ↗
2023

Hilbert Space Embedding-Based Trajectory Optimization for Multi-Modal Uncertain Obstacle Trajectory Prediction

Basant Sharma, Aditya Sharma, K.Madhava Krishna, Arun Kumar Singh
IROS 2023poster

Safe autonomous driving critically depends on how well the ego-vehicle can predict the trajectories of neighboring vehicles. To this end, several trajectory prediction algorithms have been presented in the existing literature. Many of these approaches output a multimodal distribution of obstacle tra…

Cited by 2Source ↗code ↗Scholar ↗
2023

VACNA: Visibility-Aware Cooperative Navigation With Application in Inventory Management

Houman Masnavi, Jatan Shrestha, Karl Kruusamäe, Arun Kumar Singh
RA-L 2023

This letter presents an online trajectory planning algorithm for an Unmanned Aerial Vehicle (UAV) to autonomously scan warehouse racks for inventory management. Our main motivation is to make small-sized UAVs with limited computing and sensing hardware capable of reliably performing the scanning tas

Cited by 8Source ↗Scholar ↗
2022

CCO-VOXEL: Chance Constrained Optimization over Uncertain Voxel-Grid Representation for Safe Trajectory Planning

Sudarshan S Harithas, Rishabh Dev Yadav, Deepak Singh, Arun Kumar Singh, K Madhava Krishna
ICRA 2022poster

We present CCO-VOXEL: the very first chance-constrained optimization (CCO) algorithm that can compute trajectory plans with probabilistic safety guarantees in real-time directly on the voxel-grid representation of the world. CCO-VOXEL maps the distribution over the distance to the closest obstacle t…

Cited by 8Source ↗code ↗Scholar ↗
2022

Drift Reduced Navigation with Deep Explainable Features

Mohd Omama, Sripada V. S. Sundar, Sandeep Chinchali, Arun Kumar Singh, K. Madhava Krishna
IROS 2022poster

Modern autonomous vehicles (AVs) often rely on vision, LIDAR, and even radar-based simultaneous localization and mapping (SLAM) frameworks for precise localization and navigation. However, modern SLAM frameworks often lead to unacceptably high levels of drift (i.e., localization error) when AVs obse…

Cited by 2Source ↗code ↗Scholar ↗
2022

Multi-Modal Model Predictive Control Through Batch Non-Holonomic Trajectory Optimization: Application to Highway Driving

Vivek K. Adajania, Aditya Sharma, Anish Gupta, Houman Masnavi, K. Madhava Krishna, Arun Kumar Singh
RA-L 2022

Standard Model Predictive Control (MPC) or trajectory optimization approaches perform only a local search to solve a complex non-convex optimization problem. As a result, they cannot capture the multi-modal characteristic of human driving. A global optimizer can be a potential solution but is comput

Cited by 34Source ↗code ↗Scholar ↗
2022

Visibility-Aware Navigation With Batch Projection Augmented Cross-Entropy Method Over a Learned Occlusion Cost

Houman Masnavi, Jatan Shrestha, Manav Mishra, P. B. Sujit, Karl Kruusamäe, Arun Kumar Singh
RA-L 2022

We present two real-time trajectory optimizers based on the Cross-Entropy Method for visibility-aware navigation. The two approaches differ in handling inequality constraints stemming from bounds on motion derivatives, collision avoidance, tracking error, etc. Our first optimizer augments the inequa

Cited by 22Source ↗Scholar ↗
2021

Embedded Hardware Appropriate Fast 3D Trajectory Optimization for Fixed Wing Aerial Vehicles by Leveraging Hidden Convex Structures

Vivek Kantilal Adajania, Houman Masnavi, Fatemeh Rastgar, Karl Kruusamae, Arun Kumar Singh
IROS 2021poster

Most commercially available fixed-wing aerial vehicles (FWV) can carry only small, lightweight computing hardware such as Jetson TX2 onboard. Solving non-linear trajectory optimization on these computing resources is computationally challenging even while considering only the kinematic motion model.…

Cited by 5Source ↗Scholar ↗
2021

GPU Accelerated Convex Approximations for Fast Multi-Agent Trajectory Optimization

Fatemeh Rastgar, Houman Masnavi, Jatan Shrestha, Karl Kruusamäe, Alvo Aabloo, Arun Kumar Singh
RA-L 2021

In this letter, we present a computationally efficient trajectory optimizer that can exploit GPUs to jointly compute trajectories of tens of agents in under a second. At the heart of our optimizer is a novel reformulation of the non-convex collision avoidance constraints that reduces the core comput

Cited by 15Source ↗code ↗Scholar ↗
2020

A Novel Trajectory Optimization for Affine Systems: Beyond Convex-Concave Procedure

Fatemeh Rastgar, Arun Kumar Singh, Houman Masnavi, Karl Kruusamae, Alvo Aabloo
IROS 2020poster

Trajectory optimization problems under affine motion model and convex cost function are often solved through the convex-concave procedure (CCP), wherein the non-convex collision avoidance constraints are replaced with its affine approximation. Although mathematically rigorous, CCP has some critical…

Cited by 14Source ↗Scholar ↗
2020

Bi-Convex Approximation of Non-Holonomic Trajectory Optimization

Arun Kumar Singh, Raghu Ram Theerthala, Mithun Babu, Unni Krishnan R Nair, K. Madhava Krishna
ICRA 2020poster

Autonomous cars and fixed-wing aerial vehicles have the so-called non-holonomic kinematics which non-linearly maps control input to states. As a result, trajectory optimization with such a motion model becomes highly non-linear and non-convex. In this paper, we improve the computational tractability…

Cited by 10Source ↗Scholar ↗
2020

Reactive Navigation Under Non-Parametric Uncertainty Through Hilbert Space Embedding of Probabilistic Velocity Obstacles

SriSai Naga Jyotish Poonganam, Bharath Gopalakrishnan, Venkata Seetharama Sai Bhargav Kumar Avula, Arun Kumar Singh, K. Madhava Krishna, Dinesh Manocha
RA-L 2020

The probabilistic velocity obstacle (PVO) extends the concept of velocity obstacle (VO) to work in uncertain dynamic environments. In this paper, we show how a robust model predictive control (MPC) with PVO constraints under non-parametric uncertainty can be made computationally tractable. At the co

Cited by 30Source ↗Scholar ↗
2018

Combining Method of Alternating Projections and Augmented Lagrangian for Task Constrained Trajectory Optimization

Arun Kumar Singh, Reza Ghabcheloo, Andreas Muller, Harit Pandya
IROS 2018poster

Motion planning for manipulators under task space constraints is difficult as it constrains the joint configurations to always lie on an implicitly defined manifold. It is possible to view task constrained motion planning as an optimization problem with non-linear equality constraints, which can be…

Cited by 8Source ↗Scholar ↗
2017

PRVO: Probabilistic Reciprocal Velocity Obstacle for multi robot navigation under uncertainty

Bharath Gopalakrishnan, Arun Kumar Singh, Meha Kaushik, K. Madhava Krishna, Dinesh Manocha
IROS 2017poster

We present PRVO, a probabilistic variant of Reciprocal Velocity Obstacle (RVO) for decentralized multi-robot navigation under uncertainty. PRVO characterizes the space of velocities that would allow each robot to fulfill its share in collision avoidance with a specified probability. PRVO is modeled…

Cited by 77Source ↗Scholar ↗
2015

A class of non-linear time scaling functions for smooth time optimal control along specified paths

Arun Kumar Singh, K.Madhava Krishna
IROS 2015poster

Computing time optimal motions along specified paths forms an integral part of the solution methodology for many motion planning problems. Conventionally, this optimal control problem is solved considering piece-wise constant parametrization for the control input which leads to convexity and sparsit…

Cited by 17Source ↗Scholar ↗
2015

Closed form characterization of collision free velocities and confidence bounds for non-holonomic robots in uncertain dynamic environments

Bharath Gopalakrishnan, Arun Kumar Singh, K.Madhava Krishna
IROS 2015poster

Navigating non-holonomic mobile robots in dynamic environments is challenging because it requires computing at each instant, the space of collision free velocities, characterized by a set of highly non-linear and non-convex inequalities. Moreover, uncertainty in obstacle trajectories further increas…

Cited by 15Source ↗Scholar ↗