Saksham Sharma

Saksham Sharma

I teach metal and sand how to understand space

I'm Saksham. Currently I spend my days at CMU's AIRLab watching highly educated metal boxes have existential breakdowns in the mud. When I’m not acting as a couples counselor for sensors and actuators, I am either swimming, cycling, or making some animations!

Before adopting my current brand of chaos at CMU, I spent my time sharing a sandbox with some delightfully brilliant (and unhinged) humans at Skild.ai and ARTPARK (IISc)

Recent News

  • Jan 2026 Joined MS in Robotics at CMU, working with Wenshan at AIRLab!
  • Sep 2025 Started as Robotics Engineer at Skild.ai
  • Sep 2025 Paper Reward-based Autonomous Online Learning Framework for Resilient Cooperative Target Monitoring accepted at TMLR 2025!
  • Jul 2023 Joined the AI & Robotics Lab at IISc Bangalore as Research Assistant under Prof. Suresh Sundaramm.
  • Jun 2023 Graduated from RVCE with a B.E. in ECE. Awarded Best Outgoing Student of ECE 2023 batch.

Publications

IRisPath: Enhancing Off-Road Navigation with Robust IR-RGB Fusion for Improved Day and Night Traversability
navigation

IRisPath: Enhancing Off-Road Navigation with Robust IR-RGB Fusion for Improved Day and Night Traversability

Under Submission RA-L — 2025

IRisPath fuses infrared and RGB camera streams to build robust costmaps for off-road robot navigation that remain reliable in both daylight and nighttime conditions without specialized calibration targets.

S. Sharma, A. Raizada, S. Sundaram

Distributed Online Learning for Displacement-based Formation Control
multi-robot

Distributed Online Learning for Displacement-based Formation Control

Submitted IROS'26 — 2026

A distributed online learning scheme that enables a team of robots to converge to a desired displacement-based formation without requiring a centralised coordinator or pre-computed trajectories.

S. Gupta*, S. Sharma*, S. Sundaram

Reward-based Autonomous Online Learning Framework for Resilient Cooperative Target Monitoring using a Swarm of Robots
multi-robot

Reward-based Autonomous Online Learning Framework for Resilient Cooperative Target Monitoring using a Swarm of Robots

TMLR 2025 — 2025

A consensus-based decentralised cooperative monitoring system for agile targets using swarm robots under uncertainty accepted at Transactions on Machine Learning Research.

S. Gupta, S. Sharma, S. Sundaram

Meow: Memory Evaluation through Optimized Workloads
systems

Meow: Memory Evaluation through Optimized Workloads

IEEE INDICON 2023 — 2023

An automated litmus-test synthesis tool that generates distinguishing tests between two versions of a memory model, used for formal verification of ARM's memory architecture.

S. Sharma, V. HV, M. U. Kumari

Multi Robot Path Planning Using Priority Based Algorithm
multi-robot

Multi Robot Path Planning Using Priority Based Algorithm

IEEE Connect 2022 — 2022

A priority-based decentralised algorithm for multi-robot path planning that resolves inter-agent conflicts without central coordination, demonstrated on a physical multi-robot testbed.

S. Sharma, N. A. Menezes

Pet Projects

Machine Tending Robot
manipulation

Machine Tending Robot

UR5-based robot configured with Basler camera and ROS. Uses Fourier-Mellin transform for 90ms single-reference object detection for precision pick-and-place tasks.

UR5-based machine tending robot with a Fourier-Mellin transform algorithm capable of detecting objects within 90ms using…

Autonomous Navigation Stack — Wipro-IISc SUV
navigation

Autonomous Navigation Stack — Wipro-IISc SUV

Autonomous navigation stack for SUV-scale vehicle — LiDAR-camera fusion costmap, DWA + TEB planners, LIOSAM/LOAM SLAM, and drive-by-wire control via CAN bus.

Full autonomous navigation stack for an SUV-sized vehicle developed in collaboration with Wipro and IISc, featuring LiDA…

All projects →

Thoughts? Rants? Documentation?

Server-Shenanigans

Accidentally becoming a sysadmin and lived to tell the tale

Multi Robot Planning

Indulging in the beautiful field called multi-robot path planning using Private Obstacle Path Planning algorithm

All posts →

SFX / Animation

Another hobby I dabble with — animation, SFX, and a little bit of design.
If the content deserves a dub you shall leave a sub.

Watch on YouTube →

The Master created humans first as The Lowest Type, most easily formed. Gradually, he replaced them by robots, the next higher step, and finally he created me, to take the place of the last humans.